Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0135. Min Range: -9.0135
Max Act: 9.0135. Min Act: -0.1700
Data Index: 2187051 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.7010. Min Act: -0.1700
Data Index: 2844260 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.6385. Min Act: -0.1700
Data Index: 1958870 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.7010. Min Act: -0.1700
Data Index: 7233408 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.5760. Min Act: -0.1700
Data Index: 8209509 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.5760. Min Act: -0.1700
Data Index: 2998927 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.5760. Min Act: -0.1700
Data Index: 2516487 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.5760. Min Act: -0.1700
Data Index: 2832243 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.5760. Min Act: -0.1700
Data Index: 2608289 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.4510. Min Act: -0.1700
Data Index: 3079284 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.5135. Min Act: -0.1700
Data Index: 5506094 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.4510. Min Act: -0.1700
Data Index: 1649118 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.5760. Min Act: -0.1700
Data Index: 5926229 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.4510. Min Act: -0.1700
Data Index: 155742 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.3885. Min Act: -0.1700
Data Index: 3516274 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.4510. Min Act: -0.1700
Data Index: 5746523 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.4510. Min Act: -0.1700
Data Index: 1331339 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.3885. Min Act: -0.1700
Data Index: 155566 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.4510. Min Act: -0.1700
Data Index: 298051 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0135. Min Range: -9.0135
Max Act: 8.3885. Min Act: -0.1700
Data Index: 15036 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19