Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0244. Min Range: -7.0244
Max Act: 7.0244. Min Act: -0.1700
Data Index: 1301383 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.9306. Min Act: -0.1700
Data Index: 4587751 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.8369. Min Act: -0.1700
Data Index: 4673674 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.7744. Min Act: -0.1700
Data Index: 5114504 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.7744. Min Act: -0.1700
Data Index: 5310275 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.7431. Min Act: -0.1700
Data Index: 208824 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.7119. Min Act: -0.1700
Data Index: 3031058 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.6494. Min Act: -0.1700
Data Index: 3965640 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.6181. Min Act: -0.1700
Data Index: 5026788 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.6181. Min Act: -0.1700
Data Index: 5636985 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.6181. Min Act: -0.1700
Data Index: 4369311 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.6181. Min Act: -0.1700
Data Index: 8807581 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.6181. Min Act: -0.1700
Data Index: 1931059 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.6181. Min Act: -0.1700
Data Index: 473789 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.6181. Min Act: -0.1700
Data Index: 3383026 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.5869. Min Act: -0.1700
Data Index: 4056907 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.5869. Min Act: -0.1700
Data Index: 1440618 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.5244. Min Act: -0.1700
Data Index: 5496429 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.5244. Min Act: -0.1700
Data Index: 1585540 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0244. Min Range: -7.0244
Max Act: 6.5244. Min Act: -0.1700
Data Index: 6807687 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19