Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4519 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0033. Min Range: -7.0033
Max Act: 7.0033. Min Act: -0.1700
Data Index: 3015118 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.8783. Min Act: -0.1700
Data Index: 1834594 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.6908. Min Act: -0.1700
Data Index: 5349349 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.5658. Min Act: -0.1700
Data Index: 4206206 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.4408. Min Act: -0.1700
Data Index: 1691422 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.4096. Min Act: -0.1700
Data Index: 6017340 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.3783. Min Act: -0.1700
Data Index: 3416054 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.3471. Min Act: -0.1700
Data Index: 4765823 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.3471. Min Act: -0.1700
Data Index: 2610623 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.3158. Min Act: -0.1700
Data Index: 5963753 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.3158. Min Act: -0.1700
Data Index: 532047 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.3158. Min Act: -0.1700
Data Index: 4976316 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.3158. Min Act: -0.1700
Data Index: 3390185 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.2846. Min Act: -0.1700
Data Index: 7661943 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.2846. Min Act: -0.1700
Data Index: 7730676 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.2846. Min Act: -0.1700
Data Index: 7928116 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.3158. Min Act: -0.1700
Data Index: 8104229 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.2533. Min Act: -0.1700
Data Index: 1868211 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.2533. Min Act: -0.1700
Data Index: 8630791 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0033. Min Range: -7.0033
Max Act: 6.2221. Min Act: -0.1700
Data Index: 5627788 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19