Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3712. Min Range: -9.3712
Max Act: 9.3712. Min Act: -0.1700
Data Index: 2480768 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.3712. Min Act: -0.1700
Data Index: 7292850 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.3712. Min Act: -0.1700
Data Index: 1422460 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.3712. Min Act: -0.1700
Data Index: 268851 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.3087. Min Act: -0.1700
Data Index: 1806170 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.2462. Min Act: -0.1700
Data Index: 6716272 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.2149. Min Act: -0.1700
Data Index: 397025 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.2462. Min Act: -0.1700
Data Index: 1351212 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.2149. Min Act: -0.1700
Data Index: 5122379 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.2149. Min Act: -0.1700
Data Index: 6357162 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.1837. Min Act: -0.1700
Data Index: 2950549 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.1212. Min Act: -0.1700
Data Index: 208214 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.0899. Min Act: -0.1700
Data Index: 5595331 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.0899. Min Act: -0.1700
Data Index: 4840059 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.0899. Min Act: -0.1700
Data Index: 6947649 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.0899. Min Act: -0.1700
Data Index: 2768168 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.0899. Min Act: -0.1700
Data Index: 647077 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.0899. Min Act: -0.1700
Data Index: 7380066 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.0587. Min Act: -0.1700
Data Index: 1679171 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3712. Min Range: -9.3712
Max Act: 8.0587. Min Act: -0.1700
Data Index: 5373217 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19