Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4190 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.9985. Min Act: -0.1700
Data Index: 7801327 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.5610. Min Act: -0.1700
Data Index: 757364 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.4985. Min Act: -0.1700
Data Index: 1749707 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.4985. Min Act: -0.1700
Data Index: 8189272 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.4985. Min Act: -0.1700
Data Index: 5767836 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.4985. Min Act: -0.1700
Data Index: 469444 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.4985. Min Act: -0.1700
Data Index: 3615390 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.4360. Min Act: -0.1700
Data Index: 3712211 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.3735. Min Act: -0.1700
Data Index: 3348043 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.3110. Min Act: -0.1700
Data Index: 2244015 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.3110. Min Act: -0.1700
Data Index: 2045271 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.3110. Min Act: -0.1700
Data Index: 6781673 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.3110. Min Act: -0.1700
Data Index: 5946245 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.3110. Min Act: -0.1700
Data Index: 8031500 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.3110. Min Act: -0.1700
Data Index: 4512242 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.1860. Min Act: -0.1700
Data Index: 8578543 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.2485. Min Act: -0.1700
Data Index: 2486362 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.2485. Min Act: -0.1700
Data Index: 2728843 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.2485. Min Act: -0.1700
Data Index: 8662665 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9985. Min Range: -8.9985
Max Act: 8.1235. Min Act: -0.1700
Data Index: 7517843 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19