Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 641 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.7982. Min Act: -0.1700
Data Index: 6066076 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.7982. Min Act: -0.1700
Data Index: 1451098 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.7200. Min Act: -0.1700
Data Index: 7485633 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.7357. Min Act: -0.1700
Data Index: 8333296 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.6887. Min Act: -0.1700
Data Index: 1835855 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.6105. Min Act: -0.1700
Data Index: 287053 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.6262. Min Act: -0.1700
Data Index: 4585564 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.6262. Min Act: -0.1700
Data Index: 205323 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.6105. Min Act: -0.1700
Data Index: 2543903 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.6105. Min Act: -0.1700
Data Index: 3503028 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.5949. Min Act: -0.1700
Data Index: 6092765 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.5949. Min Act: -0.1700
Data Index: 8790689 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.5792. Min Act: -0.1700
Data Index: 702548 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.5792. Min Act: -0.1700
Data Index: 4357573 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.5322. Min Act: -0.1700
Data Index: 2492256 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.5322. Min Act: -0.1700
Data Index: 8533883 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.5479. Min Act: -0.1700
Data Index: 18947 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.5636. Min Act: -0.1700
Data Index: 5148055 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.5009. Min Act: -0.1700
Data Index: 619014 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7982. Min Range: -3.7982
Max Act: 3.5166. Min Act: -0.1700
Data Index: 1696618 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19