Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1546 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.7818. Min Act: -0.1700
Data Index: 5079307 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.6256. Min Act: -0.1700
Data Index: 8177761 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.5943. Min Act: -0.1700
Data Index: 4708450 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.5318. Min Act: -0.1700
Data Index: 8777161 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.5006. Min Act: -0.1700
Data Index: 8350324 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.4693. Min Act: -0.1700
Data Index: 4188110 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.4693. Min Act: -0.1700
Data Index: 3388426 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.4068. Min Act: -0.1700
Data Index: 5809313 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.4381. Min Act: -0.1700
Data Index: 4027570 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.3443. Min Act: -0.1700
Data Index: 4245551 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.3131. Min Act: -0.1700
Data Index: 449136 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.3131. Min Act: -0.1700
Data Index: 5777220 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.3131. Min Act: -0.1700
Data Index: 4870778 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.2818. Min Act: -0.1700
Data Index: 8250452 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.2818. Min Act: -0.1700
Data Index: 4066321 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.2818. Min Act: -0.1700
Data Index: 8368884 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.2506. Min Act: -0.1700
Data Index: 3548143 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.2506. Min Act: -0.1700
Data Index: 4232304 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.2506. Min Act: -0.1700
Data Index: 2653040 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7818. Min Range: -5.7818
Max Act: 5.2193. Min Act: -0.1700
Data Index: 8173676 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19