Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5496. Min Range: -7.5496
Max Act: 7.5496. Min Act: -0.1700
Data Index: 370655 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5496. Min Range: -7.5496
Max Act: 7.4871. Min Act: -0.1700
Data Index: 4916231 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5496. Min Range: -7.5496
Max Act: 7.4558. Min Act: -0.1700
Data Index: 6749009 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5496. Min Range: -7.5496
Max Act: 7.4246. Min Act: -0.1700
Data Index: 6127584 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5496. Min Range: -7.5496
Max Act: 7.2683. Min Act: -0.1700
Data Index: 3278157 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5496. Min Range: -7.5496
Max Act: 7.1746. Min Act: -0.1700
Data Index: 2627019 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5496. Min Range: -7.5496
Max Act: 7.0808. Min Act: -0.1700
Data Index: 8688716 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5496. Min Range: -7.5496
Max Act: 7.0183. Min Act: -0.1700
Data Index: 7910865 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.9558. Min Act: -0.1700
Data Index: 2017056 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.9558. Min Act: -0.1700
Data Index: 6489410 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.8933. Min Act: -0.1700
Data Index: 8098257 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.8621. Min Act: -0.1700
Data Index: 7800971 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.8621. Min Act: -0.1700
Data Index: 5809053 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.8308. Min Act: -0.1700
Data Index: 4930726 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.7996. Min Act: -0.1700
Data Index: 3855560 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.7996. Min Act: -0.1700
Data Index: 1940444 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.7996. Min Act: -0.1700
Data Index: 4612874 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.8308. Min Act: -0.1700
Data Index: 8068946 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.7371. Min Act: -0.1700
Data Index: 8068932 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5496. Min Range: -7.5496
Max Act: 6.7683. Min Act: -0.1700
Data Index: 5286316 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19