Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1068. Min Range: -6.1068
Max Act: 6.1068. Min Act: -0.1700
Data Index: 5669633 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1068. Min Range: -6.1068
Max Act: 6.0755. Min Act: -0.1700
Data Index: 4062983 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.9193. Min Act: -0.1700
Data Index: 5060659 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.8568. Min Act: -0.1700
Data Index: 5940283 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.8255. Min Act: -0.1700
Data Index: 6865915 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.8255. Min Act: -0.1700
Data Index: 964539 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.8255. Min Act: -0.1700
Data Index: 8770091 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7943. Min Act: -0.1700
Data Index: 4886677 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.8255. Min Act: -0.1700
Data Index: 7063640 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7943. Min Act: -0.1700
Data Index: 5749659 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7943. Min Act: -0.1700
Data Index: 3815443 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7943. Min Act: -0.1700
Data Index: 8336443 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7630. Min Act: -0.1700
Data Index: 2776996 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7630. Min Act: -0.1700
Data Index: 4793903 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7943. Min Act: -0.1700
Data Index: 60072 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7630. Min Act: -0.1700
Data Index: 3177280 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7630. Min Act: -0.1700
Data Index: 7216255 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7630. Min Act: -0.1700
Data Index: 5405349 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7630. Min Act: -0.1700
Data Index: 1156355 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1068. Min Range: -6.1068
Max Act: 5.7630. Min Act: -0.1700
Data Index: 5663764 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19