Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 485 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6153. Min Range: -7.6153
Max Act: 7.6153. Min Act: -0.1700
Data Index: 2243715 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6153. Min Range: -7.6153
Max Act: 7.5840. Min Act: -0.1700
Data Index: 3822423 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6153. Min Range: -7.6153
Max Act: 7.5215. Min Act: -0.1700
Data Index: 2877626 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6153. Min Range: -7.6153
Max Act: 7.0528. Min Act: -0.1700
Data Index: 4024911 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6153. Min Range: -7.6153
Max Act: 7.0215. Min Act: -0.1700
Data Index: 1818223 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6153. Min Range: -7.6153
Max Act: 7.0215. Min Act: -0.1700
Data Index: 2497943 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.9903. Min Act: -0.1700
Data Index: 8678873 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.8965. Min Act: -0.1700
Data Index: 8671041 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.8965. Min Act: -0.1700
Data Index: 7385364 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.8965. Min Act: -0.1700
Data Index: 1137207 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.8653. Min Act: -0.1700
Data Index: 2777153 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.8340. Min Act: -0.1700
Data Index: 2038387 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.8340. Min Act: -0.1700
Data Index: 4451757 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.8028. Min Act: -0.1700
Data Index: 5132836 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.8028. Min Act: -0.1700
Data Index: 8186200 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.8028. Min Act: -0.1700
Data Index: 2716259 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.7715. Min Act: -0.1700
Data Index: 3385224 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.7403. Min Act: -0.1700
Data Index: 2200499 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.7403. Min Act: -0.1700
Data Index: 4719859 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6153. Min Range: -7.6153
Max Act: 6.7403. Min Act: -0.1700
Data Index: 5654236 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19