Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.7184. Min Act: -0.1700
Data Index: 8393764 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.6247. Min Act: -0.1700
Data Index: 7508602 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.4997. Min Act: -0.1700
Data Index: 7481799 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.4997. Min Act: -0.1700
Data Index: 1647283 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.4059. Min Act: -0.1700
Data Index: 62500 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.3747. Min Act: -0.1700
Data Index: 939114 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.3434. Min Act: -0.1700
Data Index: 3766737 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.3434. Min Act: -0.1700
Data Index: 1277977 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.2497. Min Act: -0.1700
Data Index: 7750713 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.2497. Min Act: -0.1700
Data Index: 7182359 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.2497. Min Act: -0.1700
Data Index: 6438569 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.2184. Min Act: -0.1700
Data Index: 3416485 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.2497. Min Act: -0.1700
Data Index: 3314252 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.2497. Min Act: -0.1700
Data Index: 3024749 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.2497. Min Act: -0.1700
Data Index: 1182637 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.2497. Min Act: -0.1700
Data Index: 7501187 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.2184. Min Act: -0.1700
Data Index: 8283025 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.2184. Min Act: -0.1700
Data Index: 8425796 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.1872. Min Act: -0.1700
Data Index: 6909408 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7184. Min Range: -5.7184
Max Act: 5.1872. Min Act: -0.1700
Data Index: 3148253 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19