Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3176. Min Range: -6.3176
Max Act: 6.3176. Min Act: -0.1700
Data Index: 3239678 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3176. Min Range: -6.3176
Max Act: 6.2551. Min Act: -0.1700
Data Index: 5889595 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3176. Min Range: -6.3176
Max Act: 6.1926. Min Act: -0.1700
Data Index: 5940365 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3176. Min Range: -6.3176
Max Act: 6.1301. Min Act: -0.1700
Data Index: 7410787 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3176. Min Range: -6.3176
Max Act: 6.0989. Min Act: -0.1700
Data Index: 2016889 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3176. Min Range: -6.3176
Max Act: 6.0364. Min Act: -0.1700
Data Index: 7845858 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.9739. Min Act: -0.1700
Data Index: 7926628 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.9114. Min Act: -0.1700
Data Index: 8286167 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.9114. Min Act: -0.1700
Data Index: 3374147 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.8801. Min Act: -0.1700
Data Index: 3006977 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.9114. Min Act: -0.1700
Data Index: 5413660 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.8801. Min Act: -0.1700
Data Index: 1178998 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.9114. Min Act: -0.1700
Data Index: 1202841 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.8801. Min Act: -0.1700
Data Index: 7508303 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.8801. Min Act: -0.1700
Data Index: 70344 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.8489. Min Act: -0.1700
Data Index: 2685296 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.8489. Min Act: -0.1700
Data Index: 4976762 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.8489. Min Act: -0.1700
Data Index: 7454901 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.8489. Min Act: -0.1700
Data Index: 82527 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3176. Min Range: -6.3176
Max Act: 5.8801. Min Act: -0.1700
Data Index: 3971800 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19