Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0654. Min Range: -7.0654
Max Act: 7.0654. Min Act: -0.1700
Data Index: 7074492 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.9716. Min Act: -0.1700
Data Index: 7979610 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.8466. Min Act: -0.1700
Data Index: 3737195 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.7529. Min Act: -0.1700
Data Index: 7956051 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.6279. Min Act: -0.1700
Data Index: 4476721 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.5654. Min Act: -0.1700
Data Index: 611516 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.4716. Min Act: -0.1700
Data Index: 5688196 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.4716. Min Act: -0.1700
Data Index: 8781774 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.4716. Min Act: -0.1700
Data Index: 4028955 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.4404. Min Act: -0.1700
Data Index: 8641416 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.3466. Min Act: -0.1700
Data Index: 3590752 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.2841. Min Act: -0.1700
Data Index: 7207432 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.3466. Min Act: -0.1700
Data Index: 5911510 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.3154. Min Act: -0.1700
Data Index: 8588644 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.2529. Min Act: -0.1700
Data Index: 3589916 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.2529. Min Act: -0.1700
Data Index: 364333 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.2216. Min Act: -0.1700
Data Index: 5271277 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.2529. Min Act: -0.1700
Data Index: 1399418 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.2216. Min Act: -0.1700
Data Index: 3354623 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0654. Min Range: -7.0654
Max Act: 6.2216. Min Act: -0.1700
Data Index: 1642350 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19