Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 76 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.3685. Min Act: -0.1700
Data Index: 7976208 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.3685. Min Act: -0.1700
Data Index: 4715526 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.3685. Min Act: -0.1700
Data Index: 1579318 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.3373. Min Act: -0.1700
Data Index: 7014084 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.2748. Min Act: -0.1700
Data Index: 7005521 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.2748. Min Act: -0.1700
Data Index: 8264208 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.2748. Min Act: -0.1700
Data Index: 8688418 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.2748. Min Act: -0.1700
Data Index: 8467536 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.2435. Min Act: -0.1700
Data Index: 8786801 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.2435. Min Act: -0.1700
Data Index: 8570950 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.1498. Min Act: -0.1700
Data Index: 4449839 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.1810. Min Act: -0.1700
Data Index: 2635905 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.1498. Min Act: -0.1700
Data Index: 3128914 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.1498. Min Act: -0.1700
Data Index: 3294846 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.1185. Min Act: -0.1700
Data Index: 896240 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.1498. Min Act: -0.1700
Data Index: 573785 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.1498. Min Act: -0.1700
Data Index: 2664254 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.0873. Min Act: -0.1700
Data Index: 5446492 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.0873. Min Act: -0.1700
Data Index: 1058720 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3685. Min Range: -6.3685
Max Act: 6.0560. Min Act: -0.1700
Data Index: 6493340 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19