Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2846. Min Range: -5.2846
Max Act: 5.2846. Min Act: -0.1700
Data Index: 3007023 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2846. Min Range: -5.2846
Max Act: 5.1596. Min Act: -0.1700
Data Index: 8339860 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2846. Min Range: -5.2846
Max Act: 5.0658. Min Act: -0.1700
Data Index: 3793307 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.9096. Min Act: -0.1700
Data Index: 6531625 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.8471. Min Act: -0.1700
Data Index: 3024101 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.8783. Min Act: -0.1700
Data Index: 826989 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.8158. Min Act: -0.1700
Data Index: 4965474 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.8158. Min Act: -0.1700
Data Index: 1932216 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.8158. Min Act: -0.1700
Data Index: 2099982 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.7846. Min Act: -0.1700
Data Index: 509435 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.7846. Min Act: -0.1700
Data Index: 2936192 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.7533. Min Act: -0.1700
Data Index: 7394111 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.7846. Min Act: -0.1700
Data Index: 7628118 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.6908. Min Act: -0.1700
Data Index: 3484636 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.7221. Min Act: -0.1700
Data Index: 3187118 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.7221. Min Act: -0.1700
Data Index: 3113934 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.6908. Min Act: -0.1700
Data Index: 3672581 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.6908. Min Act: -0.1700
Data Index: 4472511 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.6596. Min Act: -0.1700
Data Index: 3697538 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2846. Min Range: -5.2846
Max Act: 4.6283. Min Act: -0.1700
Data Index: 6731661 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19