Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.6005. Min Act: -0.1700
Data Index: 5015500 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.4442. Min Act: -0.1700
Data Index: 6076597 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.4442. Min Act: -0.1700
Data Index: 1996906 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.4442. Min Act: -0.1700
Data Index: 2068470 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.4130. Min Act: -0.1700
Data Index: 4475539 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.3817. Min Act: -0.1700
Data Index: 748051 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.4130. Min Act: -0.1700
Data Index: 5302558 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.3192. Min Act: -0.1700
Data Index: 274743 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.3192. Min Act: -0.1700
Data Index: 7005701 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.2567. Min Act: -0.1700
Data Index: 8437673 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.3192. Min Act: -0.1700
Data Index: 8377761 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.2880. Min Act: -0.1700
Data Index: 1158293 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.2880. Min Act: -0.1700
Data Index: 7709871 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.3192. Min Act: -0.1700
Data Index: 288576 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.2880. Min Act: -0.1700
Data Index: 3857755 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.2255. Min Act: -0.1700
Data Index: 7558917 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.2567. Min Act: -0.1700
Data Index: 4826255 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.2255. Min Act: -0.1700
Data Index: 7056127 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.2255. Min Act: -0.1700
Data Index: 4349263 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6005. Min Range: -5.6005
Max Act: 5.2567. Min Act: -0.1700
Data Index: 1979607 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19