Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3273 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4158. Min Range: -8.4158
Max Act: 8.4158. Min Act: -0.1700
Data Index: 5621490 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4158. Min Range: -8.4158
Max Act: 8.2908. Min Act: -0.1700
Data Index: 900300 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4158. Min Range: -8.4158
Max Act: 8.1971. Min Act: -0.1700
Data Index: 345048 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4158. Min Range: -8.4158
Max Act: 8.1658. Min Act: -0.1700
Data Index: 81661 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4158. Min Range: -8.4158
Max Act: 8.1346. Min Act: -0.1700
Data Index: 5445450 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4158. Min Range: -8.4158
Max Act: 8.1346. Min Act: -0.1700
Data Index: 1723901 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4158. Min Range: -8.4158
Max Act: 8.0721. Min Act: -0.1700
Data Index: 7446602 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4158. Min Range: -8.4158
Max Act: 8.0096. Min Act: -0.1700
Data Index: 8194190 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.9471. Min Act: -0.1700
Data Index: 1798365 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.9158. Min Act: -0.1700
Data Index: 1701995 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.9158. Min Act: -0.1700
Data Index: 7319861 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.8533. Min Act: -0.1700
Data Index: 7827579 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.8533. Min Act: -0.1700
Data Index: 4319578 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.8533. Min Act: -0.1700
Data Index: 8492701 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.8846. Min Act: -0.1700
Data Index: 6627447 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.8221. Min Act: -0.1700
Data Index: 1633968 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.8221. Min Act: -0.1700
Data Index: 972161 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.8221. Min Act: -0.1700
Data Index: 7946998 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.7908. Min Act: -0.1700
Data Index: 3613776 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4158. Min Range: -8.4158
Max Act: 7.7908. Min Act: -0.1700
Data Index: 2523920 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19