Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2813 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0110. Min Range: -6.0110
Max Act: 6.0110. Min Act: -0.1700
Data Index: 7678468 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.9798. Min Act: -0.1700
Data Index: 8632608 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.9173. Min Act: -0.1700
Data Index: 8804116 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.9173. Min Act: -0.1700
Data Index: 2558023 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8860. Min Act: -0.1700
Data Index: 3509277 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8860. Min Act: -0.1700
Data Index: 4910670 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8548. Min Act: -0.1700
Data Index: 2684489 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8548. Min Act: -0.1700
Data Index: 4029412 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8548. Min Act: -0.1700
Data Index: 7036934 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8235. Min Act: -0.1700
Data Index: 5424005 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.8235. Min Act: -0.1700
Data Index: 2439197 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7610. Min Act: -0.1700
Data Index: 2311598 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7923. Min Act: -0.1700
Data Index: 7745216 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7610. Min Act: -0.1700
Data Index: 8333062 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7610. Min Act: -0.1700
Data Index: 1823008 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7610. Min Act: -0.1700
Data Index: 6742608 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7298. Min Act: -0.1700
Data Index: 7133042 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.7298. Min Act: -0.1700
Data Index: 6494659 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.6985. Min Act: -0.1700
Data Index: 181571 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0110. Min Range: -6.0110
Max Act: 5.6985. Min Act: -0.1700
Data Index: 5798198 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19