Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1538 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2354. Min Range: -6.2354
Max Act: 6.2354. Min Act: -0.1700
Data Index: 6196089 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2354. Min Range: -6.2354
Max Act: 6.1104. Min Act: -0.1700
Data Index: 6196088 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2354. Min Range: -6.2354
Max Act: 6.0791. Min Act: -0.1700
Data Index: 6196091 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2354. Min Range: -6.2354
Max Act: 6.0479. Min Act: -0.1700
Data Index: 7117504 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2354. Min Range: -6.2354
Max Act: 6.0166. Min Act: -0.1700
Data Index: 3693524 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.9854. Min Act: -0.1700
Data Index: 2090909 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.9854. Min Act: -0.1700
Data Index: 6754842 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.9541. Min Act: -0.1700
Data Index: 7423786 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.9229. Min Act: -0.1700
Data Index: 7673047 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.9229. Min Act: -0.1700
Data Index: 3005813 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.8916. Min Act: -0.1700
Data Index: 2985184 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.8916. Min Act: -0.1700
Data Index: 3998436 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.7979. Min Act: -0.1700
Data Index: 1736971 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.8291. Min Act: -0.1700
Data Index: 6611336 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.7979. Min Act: -0.1700
Data Index: 6754840 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.7979. Min Act: -0.1700
Data Index: 258146 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.7979. Min Act: -0.1700
Data Index: 4654009 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.7354. Min Act: -0.1700
Data Index: 1815455 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.7354. Min Act: -0.1700
Data Index: 3591988 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2354. Min Range: -6.2354
Max Act: 5.7041. Min Act: -0.1700
Data Index: 4679150 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19