Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.6847. Min Act: -0.1700
Data Index: 3377060 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.6222. Min Act: -0.1700
Data Index: 6044247 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.5597. Min Act: -0.1700
Data Index: 8400409 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.4972. Min Act: -0.1700
Data Index: 1609887 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.4659. Min Act: -0.1700
Data Index: 1984158 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.4034. Min Act: -0.1700
Data Index: 613046 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.3722. Min Act: -0.1700
Data Index: 5725318 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.3409. Min Act: -0.1700
Data Index: 492051 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.3409. Min Act: -0.1700
Data Index: 4586507 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.3097. Min Act: -0.1700
Data Index: 1914247 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.3097. Min Act: -0.1700
Data Index: 6292790 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.2784. Min Act: -0.1700
Data Index: 6605242 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.2472. Min Act: -0.1700
Data Index: 211541 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.2472. Min Act: -0.1700
Data Index: 7175842 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.2472. Min Act: -0.1700
Data Index: 1033526 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.2472. Min Act: -0.1700
Data Index: 3513944 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.2159. Min Act: -0.1700
Data Index: 6578845 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.2472. Min Act: -0.1700
Data Index: 4442992 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.1847. Min Act: -0.1700
Data Index: 7352271 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6847. Min Range: -6.6847
Max Act: 6.2159. Min Act: -0.1700
Data Index: 1545640 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19