Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.7334. Min Act: -0.1700
Data Index: 2422698 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.6397. Min Act: -0.1700
Data Index: 808225 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.5459. Min Act: -0.1700
Data Index: 8530287 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.4522. Min Act: -0.1700
Data Index: 875886 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.4209. Min Act: -0.1700
Data Index: 1564445 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.3897. Min Act: -0.1700
Data Index: 2403748 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.3584. Min Act: -0.1700
Data Index: 1055684 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.3584. Min Act: -0.1700
Data Index: 3089946 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.3272. Min Act: -0.1700
Data Index: 7392831 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.3272. Min Act: -0.1700
Data Index: 107076 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.3272. Min Act: -0.1700
Data Index: 255529 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.2647. Min Act: -0.1700
Data Index: 7699613 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.2959. Min Act: -0.1700
Data Index: 4014579 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.3272. Min Act: -0.1700
Data Index: 217553 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.2959. Min Act: -0.1700
Data Index: 1467325 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.2959. Min Act: -0.1700
Data Index: 7174262 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.2647. Min Act: -0.1700
Data Index: 5591684 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.2647. Min Act: -0.1700
Data Index: 4204862 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.2647. Min Act: -0.1700
Data Index: 4981940 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7334. Min Range: -6.7334
Max Act: 6.2022. Min Act: -0.1700
Data Index: 3921724 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19