Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1901. Min Range: -7.1901
Max Act: 7.1901. Min Act: -0.1700
Data Index: 8149512 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1901. Min Range: -7.1901
Max Act: 7.0963. Min Act: -0.1700
Data Index: 5274713 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.9401. Min Act: -0.1700
Data Index: 4435244 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.8776. Min Act: -0.1700
Data Index: 3412779 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.8463. Min Act: -0.1700
Data Index: 7594829 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.8151. Min Act: -0.1700
Data Index: 3517287 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.7838. Min Act: -0.1700
Data Index: 6694624 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.7838. Min Act: -0.1700
Data Index: 1429884 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.8151. Min Act: -0.1700
Data Index: 2756099 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.7526. Min Act: -0.1700
Data Index: 4150126 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.7526. Min Act: -0.1700
Data Index: 3019512 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.7526. Min Act: -0.1700
Data Index: 7782808 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.7213. Min Act: -0.1700
Data Index: 3619506 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.6901. Min Act: -0.1700
Data Index: 8369649 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.6901. Min Act: -0.1700
Data Index: 910781 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.6901. Min Act: -0.1700
Data Index: 6030455 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.7213. Min Act: -0.1700
Data Index: 8750192 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.6588. Min Act: -0.1700
Data Index: 6220870 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.6276. Min Act: -0.1700
Data Index: 7262998 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1901. Min Range: -7.1901
Max Act: 6.6588. Min Act: -0.1700
Data Index: 5524653 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19