Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.4671. Min Range: -13.4671
Max Act: 13.4671. Min Act: -0.1700
Data Index: 8300231 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.4671. Min Range: -13.4671
Max Act: 13.3421. Min Act: -0.1700
Data Index: 118870 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.4671. Min Range: -13.4671
Max Act: 13.3421. Min Act: -0.1700
Data Index: 2415329 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.4671. Min Range: -13.4671
Max Act: 13.2796. Min Act: -0.1700
Data Index: 7057940 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.4671. Min Range: -13.4671
Max Act: 13.2171. Min Act: -0.1700
Data Index: 4737065 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.4671. Min Range: -13.4671
Max Act: 13.1546. Min Act: -0.1700
Data Index: 1223774 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.4671. Min Range: -13.4671
Max Act: 13.0921. Min Act: -0.1700
Data Index: 1371949 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.9046. Min Act: -0.1700
Data Index: 6631451 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.8421. Min Act: -0.1700
Data Index: 7170634 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.8421. Min Act: -0.1700
Data Index: 7157637 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.8421. Min Act: -0.1700
Data Index: 4663570 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.8421. Min Act: -0.1700
Data Index: 1231004 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.7796. Min Act: -0.1700
Data Index: 4494099 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.7171. Min Act: -0.1700
Data Index: 2962781 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.7171. Min Act: -0.1700
Data Index: 564378 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.7171. Min Act: -0.1700
Data Index: 5198573 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.6546. Min Act: -0.1700
Data Index: 6570864 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.6546. Min Act: -0.1700
Data Index: 4851803 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.6546. Min Act: -0.1700
Data Index: 7057942 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.4671. Min Range: -13.4671
Max Act: 12.5921. Min Act: -0.1700
Data Index: 6007282 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19