Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4521 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.7181. Min Act: -0.1700
Data Index: 3442345 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.7181. Min Act: -0.1700
Data Index: 5290877 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.7181. Min Act: -0.1700
Data Index: 1427448 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.4681. Min Act: -0.1700
Data Index: 3577785 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.4681. Min Act: -0.1700
Data Index: 2665014 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.2806. Min Act: -0.1700
Data Index: 7222265 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.2806. Min Act: -0.1700
Data Index: 4920503 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.3431. Min Act: -0.1700
Data Index: 7114471 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.2806. Min Act: -0.1700
Data Index: 6399684 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.1556. Min Act: -0.1700
Data Index: 4405233 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.0931. Min Act: -0.1700
Data Index: 1925511 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7181. Min Range: -8.7181
Max Act: 8.0306. Min Act: -0.1700
Data Index: 7088447 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7181. Min Range: -8.7181
Max Act: 7.9369. Min Act: -0.1700
Data Index: 2132558 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7181. Min Range: -8.7181
Max Act: 7.9056. Min Act: -0.1700
Data Index: 3366271 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7181. Min Range: -8.7181
Max Act: 7.9056. Min Act: -0.1700
Data Index: 8203120 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7181. Min Range: -8.7181
Max Act: 7.8744. Min Act: -0.1700
Data Index: 1351812 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7181. Min Range: -8.7181
Max Act: 7.8744. Min Act: -0.1700
Data Index: 7805255 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7181. Min Range: -8.7181
Max Act: 7.8119. Min Act: -0.1700
Data Index: 4553857 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7181. Min Range: -8.7181
Max Act: 7.8119. Min Act: -0.1700
Data Index: 2742057 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7181. Min Range: -8.7181
Max Act: 7.7806. Min Act: -0.1700
Data Index: 6617621 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19