Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.2367. Min Act: -0.1700
Data Index: 3028348 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.2054. Min Act: -0.1700
Data Index: 2458785 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.1742. Min Act: -0.1700
Data Index: 5095186 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.1742. Min Act: -0.1700
Data Index: 4652270 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.1429. Min Act: -0.1700
Data Index: 6669253 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.1429. Min Act: -0.1700
Data Index: 7464181 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.1429. Min Act: -0.1700
Data Index: 2300389 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.1429. Min Act: -0.1700
Data Index: 3523393 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.1429. Min Act: -0.1700
Data Index: 1952421 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.1117. Min Act: -0.1700
Data Index: 4336025 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.1117. Min Act: -0.1700
Data Index: 263409 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.0804. Min Act: -0.1700
Data Index: 1126430 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.0804. Min Act: -0.1700
Data Index: 893691 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.0804. Min Act: -0.1700
Data Index: 8662924 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.0804. Min Act: -0.1700
Data Index: 6495296 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.0804. Min Act: -0.1700
Data Index: 6421348 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.0492. Min Act: -0.1700
Data Index: 6998174 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.0492. Min Act: -0.1700
Data Index: 7271396 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.0492. Min Act: -0.1700
Data Index: 6048296 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2367. Min Range: -5.2367
Max Act: 5.0492. Min Act: -0.1700
Data Index: 6400141 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19