Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.7834. Min Act: -0.1700
Data Index: 153396 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.6896. Min Act: -0.1700
Data Index: 976433 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.5646. Min Act: -0.1700
Data Index: 863752 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.4396. Min Act: -0.1700
Data Index: 1902559 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.4396. Min Act: -0.1700
Data Index: 5841103 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.3771. Min Act: -0.1700
Data Index: 4401920 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.3146. Min Act: -0.1700
Data Index: 6033837 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.2834. Min Act: -0.1700
Data Index: 5219559 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.2834. Min Act: -0.1700
Data Index: 248420 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.2834. Min Act: -0.1700
Data Index: 1137193 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.2521. Min Act: -0.1700
Data Index: 2700600 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.1896. Min Act: -0.1700
Data Index: 8470120 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.2209. Min Act: -0.1700
Data Index: 7122995 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.1896. Min Act: -0.1700
Data Index: 5297296 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.1896. Min Act: -0.1700
Data Index: 2921235 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.1896. Min Act: -0.1700
Data Index: 6449826 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.1584. Min Act: -0.1700
Data Index: 5371326 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.1584. Min Act: -0.1700
Data Index: 1146983 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.1896. Min Act: -0.1700
Data Index: 7141620 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7834. Min Range: -6.7834
Max Act: 6.1584. Min Act: -0.1700
Data Index: 2036277 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19