Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3904 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4815. Min Range: -6.4815
Max Act: 6.4815. Min Act: -0.1700
Data Index: 5347983 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4815. Min Range: -6.4815
Max Act: 6.3252. Min Act: -0.1700
Data Index: 3703383 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4815. Min Range: -6.4815
Max Act: 6.2002. Min Act: -0.1700
Data Index: 1988749 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4815. Min Range: -6.4815
Max Act: 6.1690. Min Act: -0.1700
Data Index: 8580467 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4815. Min Range: -6.4815
Max Act: 6.2002. Min Act: -0.1700
Data Index: 1254158 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4815. Min Range: -6.4815
Max Act: 6.1690. Min Act: -0.1700
Data Index: 6036346 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4815. Min Range: -6.4815
Max Act: 6.0752. Min Act: -0.1700
Data Index: 3684545 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4815. Min Range: -6.4815
Max Act: 6.0127. Min Act: -0.1700
Data Index: 6580534 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4815. Min Range: -6.4815
Max Act: 6.0127. Min Act: -0.1700
Data Index: 1107494 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.9815. Min Act: -0.1700
Data Index: 6362377 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.9502. Min Act: -0.1700
Data Index: 641770 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.9190. Min Act: -0.1700
Data Index: 1753308 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.9502. Min Act: -0.1700
Data Index: 4561182 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.8877. Min Act: -0.1700
Data Index: 7423830 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.9190. Min Act: -0.1700
Data Index: 2498978 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.8877. Min Act: -0.1700
Data Index: 3654199 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.8877. Min Act: -0.1700
Data Index: 2587989 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.8877. Min Act: -0.1700
Data Index: 4064101 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.8565. Min Act: -0.1700
Data Index: 1714711 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4815. Min Range: -6.4815
Max Act: 5.8877. Min Act: -0.1700
Data Index: 4768049 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19