Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5998 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.6554. Min Act: -0.1700
Data Index: 5956171 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.5617. Min Act: -0.1700
Data Index: 2022795 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.5304. Min Act: -0.1700
Data Index: 6129562 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.5304. Min Act: -0.1700
Data Index: 5780462 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.5304. Min Act: -0.1700
Data Index: 5810595 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.3742. Min Act: -0.1700
Data Index: 6976499 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.3742. Min Act: -0.1700
Data Index: 7680929 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.3429. Min Act: -0.1700
Data Index: 8645390 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2804. Min Act: -0.1700
Data Index: 6605704 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2804. Min Act: -0.1700
Data Index: 4819441 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2492. Min Act: -0.1700
Data Index: 1690236 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2804. Min Act: -0.1700
Data Index: 777969 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2492. Min Act: -0.1700
Data Index: 2442012 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2492. Min Act: -0.1700
Data Index: 2030795 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2492. Min Act: -0.1700
Data Index: 690827 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2179. Min Act: -0.1700
Data Index: 3254247 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2179. Min Act: -0.1700
Data Index: 5880375 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2179. Min Act: -0.1700
Data Index: 6876217 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.2179. Min Act: -0.1700
Data Index: 936763 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6554. Min Range: -4.6554
Max Act: 4.1866. Min Act: -0.1700
Data Index: 4993134 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19