Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.8054. Min Act: -0.1700
Data Index: 3367982 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.7417. Min Act: -0.1700
Data Index: 2597365 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6777. Min Act: -0.1700
Data Index: 636308 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6937. Min Act: -0.1700
Data Index: 565077 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6777. Min Act: -0.1700
Data Index: 7100947 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6937. Min Act: -0.1700
Data Index: 6642317 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6617. Min Act: -0.1700
Data Index: 6705406 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6296. Min Act: -0.1700
Data Index: 5698297 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6135. Min Act: -0.1700
Data Index: 4288393 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6296. Min Act: -0.1700
Data Index: 6157628 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6296. Min Act: -0.1700
Data Index: 7871556 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6456. Min Act: -0.1700
Data Index: 5884893 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5974. Min Act: -0.1700
Data Index: 7419565 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6135. Min Act: -0.1700
Data Index: 270323 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5974. Min Act: -0.1700
Data Index: 2297742 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5813. Min Act: -0.1700
Data Index: 4218627 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5490. Min Act: -0.1700
Data Index: 3533903 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5652. Min Act: -0.1700
Data Index: 6187153 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5652. Min Act: -0.1700
Data Index: 5807985 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5652. Min Act: -0.1700
Data Index: 4301478 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19