Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4588 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.3952. Min Act: -0.1700
Data Index: 3262332 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.3327. Min Act: -0.1700
Data Index: 7463713 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.3327. Min Act: -0.1700
Data Index: 5265770 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.3015. Min Act: -0.1700
Data Index: 6119574 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.3015. Min Act: -0.1700
Data Index: 5342559 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.3015. Min Act: -0.1700
Data Index: 2632950 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.3015. Min Act: -0.1700
Data Index: 6840523 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.2077. Min Act: -0.1700
Data Index: 6494602 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1765. Min Act: -0.1700
Data Index: 8498988 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1765. Min Act: -0.1700
Data Index: 7237033 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1765. Min Act: -0.1700
Data Index: 1527739 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1765. Min Act: -0.1700
Data Index: 6719341 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1765. Min Act: -0.1700
Data Index: 1370836 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1452. Min Act: -0.1700
Data Index: 3398944 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1765. Min Act: -0.1700
Data Index: 1601718 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1452. Min Act: -0.1700
Data Index: 3825143 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1452. Min Act: -0.1700
Data Index: 888236 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1140. Min Act: -0.1700
Data Index: 5725438 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1140. Min Act: -0.1700
Data Index: 695124 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3952. Min Range: -6.3952
Max Act: 6.1140. Min Act: -0.1700
Data Index: 7377194 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19