Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2099 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1672. Min Range: -8.1672
Max Act: 8.1672. Min Act: -0.1700
Data Index: 5915130 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1672. Min Range: -8.1672
Max Act: 8.0734. Min Act: -0.1700
Data Index: 2954131 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.4797. Min Act: -0.1700
Data Index: 1109701 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.5109. Min Act: -0.1700
Data Index: 5523067 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.3859. Min Act: -0.1700
Data Index: 3348437 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.3547. Min Act: -0.1700
Data Index: 3601705 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.1984. Min Act: -0.1700
Data Index: 8354287 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.1672. Min Act: -0.1700
Data Index: 4603578 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.1359. Min Act: -0.1700
Data Index: 1580065 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.1359. Min Act: -0.1700
Data Index: 2183277 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.1047. Min Act: -0.1700
Data Index: 5939947 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.1047. Min Act: -0.1700
Data Index: 6218985 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.0734. Min Act: -0.1700
Data Index: 7958324 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.0734. Min Act: -0.1700
Data Index: 3492454 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.0734. Min Act: -0.1700
Data Index: 4012611 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.0422. Min Act: -0.1700
Data Index: 2456125 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.0422. Min Act: -0.1700
Data Index: 4785062 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.0109. Min Act: -0.1700
Data Index: 5939809 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1672. Min Range: -8.1672
Max Act: 7.0109. Min Act: -0.1700
Data Index: 4344408 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1672. Min Range: -8.1672
Max Act: 6.9484. Min Act: -0.1700
Data Index: 1386354 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19