Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.2353. Min Act: -0.1700
Data Index: 369420 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.2196. Min Act: -0.1700
Data Index: 7433240 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.1094. Min Act: -0.1700
Data Index: 241726 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.1252. Min Act: -0.1700
Data Index: 7099152 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.1252. Min Act: -0.1700
Data Index: 7908977 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.0779. Min Act: -0.1700
Data Index: 4054008 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.0147. Min Act: -0.1700
Data Index: 1398902 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.0147. Min Act: -0.1700
Data Index: 6352216 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.0305. Min Act: -0.1700
Data Index: 2463525 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.0147. Min Act: -0.1700
Data Index: 6062782 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.0147. Min Act: -0.1700
Data Index: 7045734 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2353. Min Range: -3.2353
Max Act: 3.0147. Min Act: -0.1700
Data Index: 682647 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2353. Min Range: -3.2353
Max Act: 2.9831. Min Act: -0.1700
Data Index: 2818480 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2353. Min Range: -3.2353
Max Act: 2.9673. Min Act: -0.1700
Data Index: 4578622 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2353. Min Range: -3.2353
Max Act: 2.9831. Min Act: -0.1700
Data Index: 7231572 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2353. Min Range: -3.2353
Max Act: 2.9673. Min Act: -0.1700
Data Index: 4938956 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2353. Min Range: -3.2353
Max Act: 2.9989. Min Act: -0.1700
Data Index: 4885734 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2353. Min Range: -3.2353
Max Act: 2.9831. Min Act: -0.1700
Data Index: 234540 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2353. Min Range: -3.2353
Max Act: 2.9831. Min Act: -0.1700
Data Index: 1681182 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2353. Min Range: -3.2353
Max Act: 2.9831. Min Act: -0.1700
Data Index: 369431 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19