Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2111 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.6312. Min Act: -0.1700
Data Index: 368607 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.5999. Min Act: -0.1700
Data Index: 3794991 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.5686. Min Act: -0.1700
Data Index: 3092409 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.5374. Min Act: -0.1700
Data Index: 880806 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.4124. Min Act: -0.1700
Data Index: 5654648 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.4124. Min Act: -0.1700
Data Index: 2208180 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3811. Min Act: -0.1700
Data Index: 5898623 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3811. Min Act: -0.1700
Data Index: 2926929 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3811. Min Act: -0.1700
Data Index: 5984449 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3811. Min Act: -0.1700
Data Index: 3244328 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3186. Min Act: -0.1700
Data Index: 3887914 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3186. Min Act: -0.1700
Data Index: 6084901 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3499. Min Act: -0.1700
Data Index: 3584689 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3499. Min Act: -0.1700
Data Index: 4225896 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3499. Min Act: -0.1700
Data Index: 3820618 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3186. Min Act: -0.1700
Data Index: 5786286 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3186. Min Act: -0.1700
Data Index: 3660891 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3186. Min Act: -0.1700
Data Index: 5734287 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3186. Min Act: -0.1700
Data Index: 4564541 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6312. Min Range: -4.6312
Max Act: 4.3186. Min Act: -0.1700
Data Index: 4403289 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19