Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5680 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.4842. Min Act: -0.1700
Data Index: 3685728 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.4530. Min Act: -0.1700
Data Index: 2286130 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.3905. Min Act: -0.1700
Data Index: 8389443 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.3280. Min Act: -0.1700
Data Index: 8554168 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.3592. Min Act: -0.1700
Data Index: 5483268 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.3280. Min Act: -0.1700
Data Index: 590313 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2967. Min Act: -0.1700
Data Index: 1631305 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2967. Min Act: -0.1700
Data Index: 2570474 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2655. Min Act: -0.1700
Data Index: 2536657 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2967. Min Act: -0.1700
Data Index: 5436202 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2967. Min Act: -0.1700
Data Index: 6557312 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2655. Min Act: -0.1700
Data Index: 106309 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2655. Min Act: -0.1700
Data Index: 106305 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2967. Min Act: -0.1700
Data Index: 5182626 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2342. Min Act: -0.1700
Data Index: 2668939 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2342. Min Act: -0.1700
Data Index: 1851682 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2342. Min Act: -0.1700
Data Index: 7594234 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2030. Min Act: -0.1700
Data Index: 2301299 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.2342. Min Act: -0.1700
Data Index: 2944239 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4842. Min Range: -5.4842
Max Act: 5.1717. Min Act: -0.1700
Data Index: 4206437 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19