Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5923 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.5380. Min Act: -0.1700
Data Index: 1365785 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.5380. Min Act: -0.1700
Data Index: 2957792 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.5067. Min Act: -0.1700
Data Index: 4698330 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.4755. Min Act: -0.1700
Data Index: 8744191 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.4130. Min Act: -0.1700
Data Index: 7099659 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.3817. Min Act: -0.1700
Data Index: 7390816 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.3505. Min Act: -0.1700
Data Index: 4043966 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.3192. Min Act: -0.1700
Data Index: 7535145 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.2880. Min Act: -0.1700
Data Index: 7317622 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.2567. Min Act: -0.1700
Data Index: 5873611 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.2567. Min Act: -0.1700
Data Index: 5425446 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.2567. Min Act: -0.1700
Data Index: 3516953 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.2255. Min Act: -0.1700
Data Index: 6570808 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.2255. Min Act: -0.1700
Data Index: 3844547 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.1942. Min Act: -0.1700
Data Index: 6619245 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.1942. Min Act: -0.1700
Data Index: 1618218 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.1942. Min Act: -0.1700
Data Index: 33871 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.1942. Min Act: -0.1700
Data Index: 3137520 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.1942. Min Act: -0.1700
Data Index: 506291 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5380. Min Range: -4.5380
Max Act: 4.1630. Min Act: -0.1700
Data Index: 7302421 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19