Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1941 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.6748. Min Act: -0.1700
Data Index: 1592662 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.5498. Min Act: -0.1700
Data Index: 5471118 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.5498. Min Act: -0.1700
Data Index: 2618170 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.5498. Min Act: -0.1700
Data Index: 4434073 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.5498. Min Act: -0.1700
Data Index: 5777292 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.5498. Min Act: -0.1700
Data Index: 2559763 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.2998. Min Act: -0.1700
Data Index: 66788 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.2373. Min Act: -0.1700
Data Index: 2926867 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.1748. Min Act: -0.1699
Data Index: 209326 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.1748. Min Act: -0.1700
Data Index: 943232 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.0498. Min Act: -0.1700
Data Index: 6968206 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.0498. Min Act: -0.1699
Data Index: 8673177 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.0498. Min Act: -0.1700
Data Index: 5777291 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.0498. Min Act: -0.1700
Data Index: 4038502 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.6748. Min Range: -15.6748
Max Act: 15.0498. Min Act: -0.1700
Data Index: 839852 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.6748. Min Range: -15.6748
Max Act: 14.9873. Min Act: -0.1700
Data Index: 5274861 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.6748. Min Range: -15.6748
Max Act: 14.9873. Min Act: -0.1700
Data Index: 8361289 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.6748. Min Range: -15.6748
Max Act: 14.8623. Min Act: -0.1699
Data Index: 3323098 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.6748. Min Range: -15.6748
Max Act: 14.9248. Min Act: -0.1700
Data Index: 140813 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.6748. Min Range: -15.6748
Max Act: 14.8623. Min Act: -0.1700
Data Index: 6861343 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19