Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2578 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.3642. Min Act: -0.1700
Data Index: 6016940 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.3329. Min Act: -0.1700
Data Index: 8168880 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.3329. Min Act: -0.1700
Data Index: 5448508 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.3017. Min Act: -0.1700
Data Index: 8352989 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.3017. Min Act: -0.1700
Data Index: 5416608 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.3017. Min Act: -0.1698
Data Index: 1230523 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.3017. Min Act: -0.1700
Data Index: 4281735 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.2391. Min Act: -0.1700
Data Index: 2422015 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.2704. Min Act: -0.1700
Data Index: 2426677 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.2704. Min Act: -0.1700
Data Index: 4460655 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.2391. Min Act: -0.1700
Data Index: 2426668 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.2079. Min Act: -0.1700
Data Index: 5642987 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.2079. Min Act: -0.1700
Data Index: 7481632 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.1766. Min Act: -0.1700
Data Index: 125412 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.1766. Min Act: -0.1700
Data Index: 610625 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.2079. Min Act: -0.1700
Data Index: 5223731 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.1766. Min Act: -0.1700
Data Index: 7524351 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.1454. Min Act: -0.1700
Data Index: 2356499 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.1454. Min Act: -0.1700
Data Index: 2890465 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3642. Min Range: -4.3642
Max Act: 4.1141. Min Act: -0.1700
Data Index: 4410917 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19