Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.3566. Min Act: -0.1700
Data Index: 7280248 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.2628. Min Act: -0.1700
Data Index: 4388509 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.1378. Min Act: -0.1700
Data Index: 3866119 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.1378. Min Act: -0.1700
Data Index: 8114711 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.1378. Min Act: -0.1700
Data Index: 1519338 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.1066. Min Act: -0.1700
Data Index: 2928468 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.1066. Min Act: -0.1700
Data Index: 3241925 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.0441. Min Act: -0.1700
Data Index: 7431967 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.0753. Min Act: -0.1700
Data Index: 6223832 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3566. Min Range: -6.3566
Max Act: 6.0128. Min Act: -0.1700
Data Index: 2450428 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9816. Min Act: -0.1700
Data Index: 5536026 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9191. Min Act: -0.1700
Data Index: 5797394 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9503. Min Act: -0.1700
Data Index: 1000777 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9503. Min Act: -0.1700
Data Index: 8383528 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9503. Min Act: -0.1700
Data Index: 2155623 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9503. Min Act: -0.1700
Data Index: 7883444 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9503. Min Act: -0.1700
Data Index: 7216992 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9503. Min Act: -0.1700
Data Index: 1123436 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9191. Min Act: -0.1700
Data Index: 1782782 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3566. Min Range: -6.3566
Max Act: 5.9191. Min Act: -0.1700
Data Index: 2196241 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19