Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.3806. Min Act: -0.1700
Data Index: 3034767 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.4119. Min Act: -0.1700
Data Index: 6073430 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.2556. Min Act: -0.1700
Data Index: 7161551 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.2556. Min Act: -0.1700
Data Index: 2884720 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.2244. Min Act: -0.1700
Data Index: 4024325 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.1619. Min Act: -0.1700
Data Index: 258467 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.1931. Min Act: -0.1700
Data Index: 60379 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.2244. Min Act: -0.1700
Data Index: 2578804 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.2244. Min Act: -0.1700
Data Index: 1914277 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.1306. Min Act: -0.1700
Data Index: 2407372 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.1619. Min Act: -0.1700
Data Index: 7599584 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.1306. Min Act: -0.1700
Data Index: 7731310 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.1306. Min Act: -0.1700
Data Index: 2837932 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.1619. Min Act: -0.1700
Data Index: 5708573 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.0994. Min Act: -0.1700
Data Index: 8720487 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.1306. Min Act: -0.1700
Data Index: 7920327 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.1306. Min Act: -0.1700
Data Index: 5091475 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.0681. Min Act: -0.1700
Data Index: 2468349 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.0994. Min Act: -0.1700
Data Index: 5695902 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4119. Min Range: -6.4119
Max Act: 6.0681. Min Act: -0.1700
Data Index: 2673407 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19