Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.3326. Min Act: -0.1700
Data Index: 2502582 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.2701. Min Act: -0.1700
Data Index: 2948338 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.2701. Min Act: -0.1700
Data Index: 1832948 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.2701. Min Act: -0.1700
Data Index: 8387742 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.2701. Min Act: -0.1700
Data Index: 4125587 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.2076. Min Act: -0.1700
Data Index: 60158 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.2076. Min Act: -0.1700
Data Index: 6618726 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1763. Min Act: -0.1700
Data Index: 1289036 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1763. Min Act: -0.1700
Data Index: 5062841 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1763. Min Act: -0.1700
Data Index: 609556 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1763. Min Act: -0.1700
Data Index: 7038503 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.2076. Min Act: -0.1700
Data Index: 7765129 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1451. Min Act: -0.1700
Data Index: 5639503 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1138. Min Act: -0.1700
Data Index: 8806259 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1451. Min Act: -0.1700
Data Index: 1728521 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1138. Min Act: -0.1700
Data Index: 3364053 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1138. Min Act: -0.1700
Data Index: 8233861 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1138. Min Act: -0.1700
Data Index: 7269716 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1138. Min Act: -0.1700
Data Index: 1683210 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3326. Min Range: -7.3326
Max Act: 7.1138. Min Act: -0.1700
Data Index: 7536380 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19