Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4177 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.5538. Min Act: -0.1700
Data Index: 6103486 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.5852. Min Act: -0.1700
Data Index: 3378246 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4912. Min Act: -0.1700
Data Index: 4523289 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4912. Min Act: -0.1697
Data Index: 4762587 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4599. Min Act: -0.1698
Data Index: 3575238 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4599. Min Act: -0.1700
Data Index: 3383885 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4599. Min Act: -0.1700
Data Index: 6494183 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4599. Min Act: -0.1700
Data Index: 1446125 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1700
Data Index: 1011048 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1697
Data Index: 2410509 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1700
Data Index: 1995579 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1700
Data Index: 6074247 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1700
Data Index: 4957854 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1699
Data Index: 4901607 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1700
Data Index: 2439273 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1700
Data Index: 2259158 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1700
Data Index: 1982248 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1700
Data Index: 8533054 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1700
Data Index: 4428365 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5852. Min Range: -3.5852
Max Act: 3.4285. Min Act: -0.1700
Data Index: 8713951 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19