Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6394 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0744. Min Range: -7.0744
Max Act: 7.0744. Min Act: -0.1700
Data Index: 6719272 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.8869. Min Act: -0.1700
Data Index: 4477633 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.7306. Min Act: -0.1700
Data Index: 3091394 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.6369. Min Act: -0.1700
Data Index: 8746717 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.6056. Min Act: -0.1700
Data Index: 5936286 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.5744. Min Act: -0.1700
Data Index: 8495225 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.5119. Min Act: -0.1700
Data Index: 4292068 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.4806. Min Act: -0.1700
Data Index: 3550784 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.4806. Min Act: -0.1700
Data Index: 3550785 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.4806. Min Act: -0.1700
Data Index: 4292059 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.4494. Min Act: -0.1700
Data Index: 6206841 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.4806. Min Act: -0.1700
Data Index: 5557638 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.4494. Min Act: -0.1700
Data Index: 7778805 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.4181. Min Act: -0.1700
Data Index: 6866941 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.3244. Min Act: -0.1700
Data Index: 4252585 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.3244. Min Act: -0.1700
Data Index: 784073 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.2619. Min Act: -0.1700
Data Index: 1831362 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.2931. Min Act: -0.1700
Data Index: 7108816 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.2931. Min Act: -0.1700
Data Index: 6206836 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0744. Min Range: -7.0744
Max Act: 6.2931. Min Act: -0.1700
Data Index: 1704222 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19