Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.7912. Min Act: -0.1700
Data Index: 7331274 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.8225. Min Act: -0.1700
Data Index: 6868843 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.8225. Min Act: -0.1700
Data Index: 837276 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.7287. Min Act: -0.1700
Data Index: 5110710 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6662. Min Act: -0.1700
Data Index: 5223709 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6662. Min Act: -0.1700
Data Index: 647306 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6662. Min Act: -0.1700
Data Index: 4181648 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6350. Min Act: -0.1700
Data Index: 198775 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6350. Min Act: -0.1700
Data Index: 8735141 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6350. Min Act: -0.1700
Data Index: 225948 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5725. Min Act: -0.1700
Data Index: 406065 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5725. Min Act: -0.1700
Data Index: 7227459 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5725. Min Act: -0.1700
Data Index: 7348997 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5725. Min Act: -0.1700
Data Index: 355718 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5725. Min Act: -0.1700
Data Index: 2795580 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5725. Min Act: -0.1700
Data Index: 2450933 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5412. Min Act: -0.1700
Data Index: 3166122 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5100. Min Act: -0.1700
Data Index: 3751293 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5412. Min Act: -0.1700
Data Index: 832830 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5412. Min Act: -0.1700
Data Index: 3286805 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19