Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2726 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2714. Min Range: -6.2714
Max Act: 6.2714. Min Act: -0.1700
Data Index: 3522258 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2714. Min Range: -6.2714
Max Act: 6.2089. Min Act: -0.1700
Data Index: 1279852 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2714. Min Range: -6.2714
Max Act: 6.0839. Min Act: -0.1700
Data Index: 8630941 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2714. Min Range: -6.2714
Max Act: 6.0839. Min Act: -0.1700
Data Index: 8358682 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2714. Min Range: -6.2714
Max Act: 6.0839. Min Act: -0.1700
Data Index: 2672394 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2714. Min Range: -6.2714
Max Act: 6.0526. Min Act: -0.1700
Data Index: 3688313 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2714. Min Range: -6.2714
Max Act: 6.0526. Min Act: -0.1700
Data Index: 4137290 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.9901. Min Act: -0.1700
Data Index: 347172 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.9589. Min Act: -0.1700
Data Index: 3595934 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.9901. Min Act: -0.1700
Data Index: 7407937 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.9589. Min Act: -0.1700
Data Index: 2706206 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.9901. Min Act: -0.1700
Data Index: 1170914 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.9589. Min Act: -0.1700
Data Index: 1118412 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.9276. Min Act: -0.1700
Data Index: 4145264 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.8651. Min Act: -0.1700
Data Index: 5592012 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.8964. Min Act: -0.1700
Data Index: 7303995 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.9276. Min Act: -0.1700
Data Index: 266539 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.8964. Min Act: -0.1700
Data Index: 7464116 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.8964. Min Act: -0.1700
Data Index: 851980 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2714. Min Range: -6.2714
Max Act: 5.8964. Min Act: -0.1700
Data Index: 8002484 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19