Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.6609. Min Act: -0.1700
Data Index: 5193265 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.5359. Min Act: -0.1700
Data Index: 6116067 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.5046. Min Act: -0.1700
Data Index: 7338221 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.4734. Min Act: -0.1700
Data Index: 3570998 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.3796. Min Act: -0.1700
Data Index: 4280752 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.3796. Min Act: -0.1700
Data Index: 7165447 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.3484. Min Act: -0.1700
Data Index: 7678187 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.3171. Min Act: -0.1700
Data Index: 6915456 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.3171. Min Act: -0.1700
Data Index: 6467515 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.3171. Min Act: -0.1700
Data Index: 6157152 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.2859. Min Act: -0.1700
Data Index: 6168916 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.2234. Min Act: -0.1700
Data Index: 4094287 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.2546. Min Act: -0.1700
Data Index: 423334 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.2546. Min Act: -0.1700
Data Index: 7706744 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.2234. Min Act: -0.1700
Data Index: 1955676 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.2234. Min Act: -0.1700
Data Index: 7874340 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.2234. Min Act: -0.1700
Data Index: 3503504 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1921. Min Act: -0.1700
Data Index: 6352857 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1296. Min Act: -0.1700
Data Index: 5345016 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1296. Min Act: -0.1700
Data Index: 877778 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19