Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4440 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.5223. Min Act: -0.1700
Data Index: 3370443 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.4598. Min Act: -0.1700
Data Index: 4233994 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.4285. Min Act: -0.1700
Data Index: 1185218 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.4598. Min Act: -0.1700
Data Index: 628418 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.4285. Min Act: -0.1700
Data Index: 8735483 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.4285. Min Act: -0.1700
Data Index: 1441809 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.4285. Min Act: -0.1700
Data Index: 4306716 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3660. Min Act: -0.1700
Data Index: 1972797 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3660. Min Act: -0.1700
Data Index: 416566 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3660. Min Act: -0.1700
Data Index: 2745417 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3348. Min Act: -0.1700
Data Index: 6987449 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3660. Min Act: -0.1700
Data Index: 4683596 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3660. Min Act: -0.1700
Data Index: 7374149 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3660. Min Act: -0.1700
Data Index: 953985 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3660. Min Act: -0.1700
Data Index: 3488153 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3660. Min Act: -0.1700
Data Index: 1216294 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3660. Min Act: -0.1700
Data Index: 7681991 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3035. Min Act: -0.1700
Data Index: 4111351 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3348. Min Act: -0.1700
Data Index: 5784935 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5223. Min Range: -5.5223
Max Act: 5.3348. Min Act: -0.1700
Data Index: 893624 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19