Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.9166. Min Act: -0.1700
Data Index: 7166546 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.9008. Min Act: -0.1700
Data Index: 4571800 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.8690. Min Act: -0.1700
Data Index: 6952201 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.9166. Min Act: -0.1700
Data Index: 6274462 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.8532. Min Act: -0.1700
Data Index: 2019017 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.8373. Min Act: -0.1700
Data Index: 5787697 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.8373. Min Act: -0.1700
Data Index: 3848364 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.8054. Min Act: -0.1700
Data Index: 863781 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.8214. Min Act: -0.1700
Data Index: 5936946 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.8054. Min Act: -0.1700
Data Index: 3224003 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.7895. Min Act: -0.1700
Data Index: 6689359 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.8214. Min Act: -0.1700
Data Index: 6195604 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.8054. Min Act: -0.1700
Data Index: 5161858 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.8214. Min Act: -0.1700
Data Index: 8167633 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.7895. Min Act: -0.1700
Data Index: 63552 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.7895. Min Act: -0.1700
Data Index: 3149322 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.7736. Min Act: -0.1700
Data Index: 7229549 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.7736. Min Act: -0.1700
Data Index: 555240 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.7736. Min Act: -0.1700
Data Index: 4103885 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9166. Min Range: -2.9166
Max Act: 2.7576. Min Act: -0.1700
Data Index: 6952209 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19