Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0417. Min Range: -8.0417
Max Act: 8.0417. Min Act: -0.1700
Data Index: 1923377 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.6355. Min Act: -0.1700
Data Index: 6576711 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.5417. Min Act: -0.1700
Data Index: 7812964 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.5105. Min Act: -0.1700
Data Index: 7258684 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.4480. Min Act: -0.1700
Data Index: 31108 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.4480. Min Act: -0.1700
Data Index: 6201300 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.4167. Min Act: -0.1700
Data Index: 5123334 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.3542. Min Act: -0.1700
Data Index: 8106416 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.3230. Min Act: -0.1700
Data Index: 6595171 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.3230. Min Act: -0.1700
Data Index: 1898488 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.3230. Min Act: -0.1700
Data Index: 1252894 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.2917. Min Act: -0.1700
Data Index: 7836021 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.2605. Min Act: -0.1700
Data Index: 3647871 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.2605. Min Act: -0.1700
Data Index: 6056342 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.2605. Min Act: -0.1700
Data Index: 7509054 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.2292. Min Act: -0.1700
Data Index: 2579329 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.2292. Min Act: -0.1700
Data Index: 7462802 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.1980. Min Act: -0.1700
Data Index: 3889699 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.1667. Min Act: -0.1700
Data Index: 7877911 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0417. Min Range: -8.0417
Max Act: 7.1667. Min Act: -0.1700
Data Index: 4526630 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19