Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3229. Min Range: -5.3229
Max Act: 5.3229. Min Act: -0.1700
Data Index: 1938134 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.8854. Min Act: -0.1700
Data Index: 5576466 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.7917. Min Act: -0.1700
Data Index: 8456684 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.7917. Min Act: -0.1700
Data Index: 4995084 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.7917. Min Act: -0.1700
Data Index: 5249891 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.7292. Min Act: -0.1700
Data Index: 3496510 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.7292. Min Act: -0.1700
Data Index: 632057 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.7292. Min Act: -0.1700
Data Index: 7162454 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6979. Min Act: -0.1700
Data Index: 5043544 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6979. Min Act: -0.1700
Data Index: 7637697 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6667. Min Act: -0.1700
Data Index: 351326 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6354. Min Act: -0.1700
Data Index: 804291 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6667. Min Act: -0.1700
Data Index: 6835935 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6667. Min Act: -0.1700
Data Index: 7294037 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6354. Min Act: -0.1700
Data Index: 4519501 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6354. Min Act: -0.1700
Data Index: 6476384 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6042. Min Act: -0.1700
Data Index: 7637693 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6042. Min Act: -0.1700
Data Index: 1275139 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6042. Min Act: -0.1700
Data Index: 6497452 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3229. Min Range: -5.3229
Max Act: 4.6042. Min Act: -0.1700
Data Index: 2552467 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19