Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3939 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.7544. Min Act: -0.1700
Data Index: 2758708 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6607. Min Act: -0.1700
Data Index: 4990462 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6607. Min Act: -0.1700
Data Index: 2758706 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5669. Min Act: -0.1700
Data Index: 6696692 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5982. Min Act: -0.1700
Data Index: 1612771 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5982. Min Act: -0.1700
Data Index: 6248242 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5669. Min Act: -0.1700
Data Index: 3041098 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5357. Min Act: -0.1700
Data Index: 5073478 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5357. Min Act: -0.1700
Data Index: 1612772 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5357. Min Act: -0.1700
Data Index: 3260772 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5669. Min Act: -0.1700
Data Index: 6232008 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5357. Min Act: -0.1700
Data Index: 262364 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5044. Min Act: -0.1700
Data Index: 1260164 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.4732. Min Act: -0.1700
Data Index: 3487128 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.4419. Min Act: -0.1700
Data Index: 2734439 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.4107. Min Act: -0.1700
Data Index: 4385791 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.4107. Min Act: -0.1700
Data Index: 4896895 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.4107. Min Act: -0.1700
Data Index: 5856574 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.4107. Min Act: -0.1700
Data Index: 7630564 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.3794. Min Act: -0.1700
Data Index: 656170 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19