Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2835. Min Range: -7.2835
Max Act: 7.2835. Min Act: -0.1700
Data Index: 6895005 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.8772. Min Act: -0.1700
Data Index: 4612869 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.6897. Min Act: -0.1700
Data Index: 318090 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.6272. Min Act: -0.1700
Data Index: 2176807 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.6272. Min Act: -0.1700
Data Index: 5009462 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.5335. Min Act: -0.1700
Data Index: 3941352 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.5335. Min Act: -0.1700
Data Index: 4549200 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.5022. Min Act: -0.1700
Data Index: 5872423 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.5022. Min Act: -0.1700
Data Index: 1577014 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.4710. Min Act: -0.1700
Data Index: 3834273 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.4710. Min Act: -0.1700
Data Index: 8763171 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.4397. Min Act: -0.1700
Data Index: 1415459 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.4397. Min Act: -0.1700
Data Index: 8559105 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.4397. Min Act: -0.1700
Data Index: 5539200 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.3772. Min Act: -0.1700
Data Index: 8675274 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.4085. Min Act: -0.1700
Data Index: 8453223 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.4085. Min Act: -0.1700
Data Index: 2318044 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.3772. Min Act: -0.1700
Data Index: 5756038 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.3772. Min Act: -0.1700
Data Index: 1446564 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2835. Min Range: -7.2835
Max Act: 6.3772. Min Act: -0.1700
Data Index: 3258362 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19