Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3117 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.4139. Min Act: -0.1700
Data Index: 952568 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3983. Min Act: -0.1700
Data Index: 3524030 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3826. Min Act: -0.1700
Data Index: 6300741 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3669. Min Act: -0.1700
Data Index: 3291598 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3669. Min Act: -0.1700
Data Index: 479993 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3669. Min Act: -0.1700
Data Index: 4005127 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3512. Min Act: -0.1700
Data Index: 3349617 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3512. Min Act: -0.1700
Data Index: 8216969 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3512. Min Act: -0.1700
Data Index: 2144198 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3512. Min Act: -0.1700
Data Index: 6129821 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3198. Min Act: -0.1700
Data Index: 2930573 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3198. Min Act: -0.1700
Data Index: 2684520 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3355. Min Act: -0.1700
Data Index: 2213471 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3512. Min Act: -0.1700
Data Index: 5083136 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3198. Min Act: -0.1700
Data Index: 5725618 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3198. Min Act: -0.1700
Data Index: 329392 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3198. Min Act: -0.1700
Data Index: 1046921 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3355. Min Act: -0.1700
Data Index: 5416299 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3355. Min Act: -0.1700
Data Index: 6166499 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4139. Min Range: -3.4139
Max Act: 3.3198. Min Act: -0.1700
Data Index: 4888598 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19