Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3691 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5221. Min Range: -7.5221
Max Act: 7.5221. Min Act: -0.1700
Data Index: 8814095 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5221. Min Range: -7.5221
Max Act: 7.4283. Min Act: -0.1700
Data Index: 8304872 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5221. Min Range: -7.5221
Max Act: 7.1471. Min Act: -0.1700
Data Index: 3355098 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5221. Min Range: -7.5221
Max Act: 7.1471. Min Act: -0.1700
Data Index: 8713396 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5221. Min Range: -7.5221
Max Act: 7.0846. Min Act: -0.1700
Data Index: 4852086 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5221. Min Range: -7.5221
Max Act: 7.0221. Min Act: -0.1700
Data Index: 6965103 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5221. Min Range: -7.5221
Max Act: 7.0221. Min Act: -0.1700
Data Index: 2368830 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.9908. Min Act: -0.1700
Data Index: 1724537 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.9596. Min Act: -0.1700
Data Index: 2615706 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.9596. Min Act: -0.1700
Data Index: 4878791 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.9283. Min Act: -0.1700
Data Index: 6485812 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.9283. Min Act: -0.1700
Data Index: 2104166 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.8971. Min Act: -0.1700
Data Index: 8140144 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.8346. Min Act: -0.1700
Data Index: 7617260 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.8346. Min Act: -0.1700
Data Index: 8111967 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.8346. Min Act: -0.1700
Data Index: 2972190 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.8033. Min Act: -0.1700
Data Index: 5706903 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.7721. Min Act: -0.1700
Data Index: 1628362 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.7408. Min Act: -0.1700
Data Index: 7861681 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5221. Min Range: -7.5221
Max Act: 6.7408. Min Act: -0.1700
Data Index: 6514749 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19