Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5281 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.4325. Min Act: -0.1700
Data Index: 818392 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.3388. Min Act: -0.1700
Data Index: 2717396 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.1513. Min Act: -0.1700
Data Index: 3003864 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.1200. Min Act: -0.1700
Data Index: 8577409 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.0888. Min Act: -0.1700
Data Index: 5703177 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.0888. Min Act: -0.1700
Data Index: 728417 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.0888. Min Act: -0.1700
Data Index: 6430048 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.0575. Min Act: -0.1700
Data Index: 1955596 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.0575. Min Act: -0.1700
Data Index: 7231594 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.0263. Min Act: -0.1700
Data Index: 1434529 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.0263. Min Act: -0.1700
Data Index: 132722 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4325. Min Range: -7.4325
Max Act: 7.0263. Min Act: -0.1700
Data Index: 6630603 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4325. Min Range: -7.4325
Max Act: 6.9950. Min Act: -0.1700
Data Index: 382664 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4325. Min Range: -7.4325
Max Act: 6.9950. Min Act: -0.1700
Data Index: 128731 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4325. Min Range: -7.4325
Max Act: 6.9950. Min Act: -0.1700
Data Index: 1486870 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4325. Min Range: -7.4325
Max Act: 6.9950. Min Act: -0.1700
Data Index: 840700 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4325. Min Range: -7.4325
Max Act: 6.9325. Min Act: -0.1700
Data Index: 1103478 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4325. Min Range: -7.4325
Max Act: 6.9638. Min Act: -0.1700
Data Index: 8264956 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4325. Min Range: -7.4325
Max Act: 6.9950. Min Act: -0.1700
Data Index: 1959542 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4325. Min Range: -7.4325
Max Act: 6.9638. Min Act: -0.1700
Data Index: 7092309 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19