Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1201 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.8791. Min Act: -0.1700
Data Index: 768509 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.7541. Min Act: -0.1700
Data Index: 5594616 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.5041. Min Act: -0.1700
Data Index: 3432807 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.3791. Min Act: -0.1700
Data Index: 6531327 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.2541. Min Act: -0.1700
Data Index: 8109239 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 4190231 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.0978. Min Act: -0.1700
Data Index: 18252 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.0353. Min Act: -0.1700
Data Index: 7682234 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.9416. Min Act: -0.1700
Data Index: 338671 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.9416. Min Act: -0.1700
Data Index: 7809935 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.8791. Min Act: -0.1700
Data Index: 6240064 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.8478. Min Act: -0.1700
Data Index: 7738201 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.7853. Min Act: -0.1700
Data Index: 5247174 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.8166. Min Act: -0.1700
Data Index: 6412443 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.7541. Min Act: -0.1700
Data Index: 5716296 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.7853. Min Act: -0.1700
Data Index: 1929735 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.7228. Min Act: -0.1700
Data Index: 3778021 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.7541. Min Act: -0.1700
Data Index: 1951754 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.6916. Min Act: -0.1685
Data Index: 1290218 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8791. Min Range: -8.8791
Max Act: 7.7228. Min Act: -0.1700
Data Index: 3006416 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19