Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.9945. Min Act: -0.1700
Data Index: 5328529 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.9007. Min Act: -0.1700
Data Index: 3006216 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.8695. Min Act: -0.1700
Data Index: 5698175 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.8382. Min Act: -0.1700
Data Index: 3896871 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.7287. Min Act: -0.1700
Data Index: 4190625 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6974. Min Act: -0.1700
Data Index: 5397234 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6974. Min Act: -0.1700
Data Index: 1971493 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6974. Min Act: -0.1700
Data Index: 8226360 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6662. Min Act: -0.1700
Data Index: 2003565 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6505. Min Act: -0.1700
Data Index: 1352293 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6662. Min Act: -0.1700
Data Index: 4430354 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6505. Min Act: -0.1700
Data Index: 5071258 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6505. Min Act: -0.1700
Data Index: 8117228 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6349. Min Act: -0.1700
Data Index: 561177 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6349. Min Act: -0.1700
Data Index: 1674579 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6349. Min Act: -0.1700
Data Index: 747930 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6192. Min Act: -0.1700
Data Index: 5464903 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6192. Min Act: -0.1700
Data Index: 3626957 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6192. Min Act: -0.1700
Data Index: 3103154 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9945. Min Range: -3.9945
Max Act: 3.6036. Min Act: -0.1700
Data Index: 6080318 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19