Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2248. Min Range: -6.2248
Max Act: 6.2248. Min Act: -0.1700
Data Index: 505326 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2248. Min Range: -6.2248
Max Act: 6.2248. Min Act: -0.1700
Data Index: 3150398 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2248. Min Range: -6.2248
Max Act: 6.0060. Min Act: -0.1700
Data Index: 1614088 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2248. Min Range: -6.2248
Max Act: 6.0060. Min Act: -0.1700
Data Index: 3420057 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2248. Min Range: -6.2248
Max Act: 6.0060. Min Act: -0.1700
Data Index: 4226520 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.9748. Min Act: -0.1700
Data Index: 7424251 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.9435. Min Act: -0.1700
Data Index: 7470062 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.9123. Min Act: -0.1700
Data Index: 6890403 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.8810. Min Act: -0.1700
Data Index: 115382 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.8498. Min Act: -0.1700
Data Index: 8241387 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.8498. Min Act: -0.1700
Data Index: 3420055 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.8498. Min Act: -0.1700
Data Index: 8490251 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.8498. Min Act: -0.1700
Data Index: 475691 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.8498. Min Act: -0.1700
Data Index: 7424269 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.8185. Min Act: -0.1700
Data Index: 1881404 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.8185. Min Act: -0.1700
Data Index: 1170979 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.7873. Min Act: -0.1700
Data Index: 3467027 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.7873. Min Act: -0.1700
Data Index: 3150400 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.7560. Min Act: -0.1700
Data Index: 1614087 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2248. Min Range: -6.2248
Max Act: 5.7248. Min Act: -0.1700
Data Index: 199695 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19