Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1244 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.6207. Min Act: -0.1700
Data Index: 5652355 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.5270. Min Act: -0.1700
Data Index: 3543921 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.5270. Min Act: -0.1700
Data Index: 2047634 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.4957. Min Act: -0.1700
Data Index: 3394832 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.5270. Min Act: -0.1700
Data Index: 3154101 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.4645. Min Act: -0.1700
Data Index: 2115419 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.4332. Min Act: -0.1700
Data Index: 5668601 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.4332. Min Act: -0.1700
Data Index: 6596121 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.4020. Min Act: -0.1700
Data Index: 6241483 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.4332. Min Act: -0.1700
Data Index: 3109159 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.4020. Min Act: -0.1700
Data Index: 2115413 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.3395. Min Act: -0.1700
Data Index: 1439871 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.3395. Min Act: -0.1700
Data Index: 1334566 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.3395. Min Act: -0.1700
Data Index: 6369981 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.3395. Min Act: -0.1700
Data Index: 6954128 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.3395. Min Act: -0.1700
Data Index: 5401072 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.3395. Min Act: -0.1700
Data Index: 4963641 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.3395. Min Act: -0.1700
Data Index: 2115415 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.3082. Min Act: -0.1700
Data Index: 545538 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6207. Min Range: -5.6207
Max Act: 5.3082. Min Act: -0.1700
Data Index: 3249131 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19