Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5095 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.6196. Min Act: -0.1700
Data Index: 1911088 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.3696. Min Act: -0.1700
Data Index: 3926746 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.3384. Min Act: -0.1700
Data Index: 5480343 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.3071. Min Act: -0.1700
Data Index: 4589640 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.2759. Min Act: -0.1700
Data Index: 8330878 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.2134. Min Act: -0.1700
Data Index: 7177941 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.1509. Min Act: -0.1700
Data Index: 4067723 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.0571. Min Act: -0.1700
Data Index: 5440328 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.0571. Min Act: -0.1700
Data Index: 4634821 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.0259. Min Act: -0.1700
Data Index: 7892074 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.0259. Min Act: -0.1700
Data Index: 5179682 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.0259. Min Act: -0.1700
Data Index: 960605 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6196. Min Range: -7.6196
Max Act: 7.0259. Min Act: -0.1700
Data Index: 3066031 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6196. Min Range: -7.6196
Max Act: 6.9321. Min Act: -0.1700
Data Index: 8051290 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6196. Min Range: -7.6196
Max Act: 6.9634. Min Act: -0.1700
Data Index: 2523567 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6196. Min Range: -7.6196
Max Act: 6.9634. Min Act: -0.1700
Data Index: 7109600 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6196. Min Range: -7.6196
Max Act: 6.9634. Min Act: -0.1700
Data Index: 1507668 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6196. Min Range: -7.6196
Max Act: 6.9321. Min Act: -0.1700
Data Index: 7156919 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6196. Min Range: -7.6196
Max Act: 6.9321. Min Act: -0.1700
Data Index: 1520190 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6196. Min Range: -7.6196
Max Act: 6.9009. Min Act: -0.1700
Data Index: 3047708 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19