Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3840 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.4494. Min Act: -0.1700
Data Index: 4345069 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.4024. Min Act: -0.1700
Data Index: 866901 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.3554. Min Act: -0.1700
Data Index: 7746847 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.2297. Min Act: -0.1700
Data Index: 8245160 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.2140. Min Act: -0.1700
Data Index: 8658133 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.1511. Min Act: -0.1700
Data Index: 8318796 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.1196. Min Act: -0.1700
Data Index: 1689722 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.1039. Min Act: -0.1700
Data Index: 5487663 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0881. Min Act: -0.1700
Data Index: 6825112 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0881. Min Act: -0.1700
Data Index: 1181787 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0565. Min Act: -0.1700
Data Index: 7584801 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0565. Min Act: -0.1700
Data Index: 7876477 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0250. Min Act: -0.1700
Data Index: 8787222 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0408. Min Act: -0.1700
Data Index: 6753291 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0408. Min Act: -0.1700
Data Index: 2154156 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0408. Min Act: -0.1700
Data Index: 977467 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0250. Min Act: -0.1700
Data Index: 3145197 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0092. Min Act: -0.1700
Data Index: 476650 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0408. Min Act: -0.1700
Data Index: 1239383 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4494. Min Range: -3.4494
Max Act: 3.0250. Min Act: -0.1700
Data Index: 3852571 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19