Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4774 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3838. Min Range: -7.3838
Max Act: 7.3838. Min Act: -0.1700
Data Index: 5591726 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3838. Min Range: -7.3838
Max Act: 7.0401. Min Act: -0.1700
Data Index: 5428554 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.5713. Min Act: -0.1700
Data Index: 2300255 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.4776. Min Act: -0.1700
Data Index: 3435736 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.4776. Min Act: -0.1700
Data Index: 5183878 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.4463. Min Act: -0.1700
Data Index: 690814 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.4463. Min Act: -0.1700
Data Index: 6457205 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.4151. Min Act: -0.1700
Data Index: 373237 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.3838. Min Act: -0.1700
Data Index: 909089 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.3838. Min Act: -0.1700
Data Index: 2211108 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.2901. Min Act: -0.1700
Data Index: 3712639 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.2901. Min Act: -0.1700
Data Index: 7536943 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.2901. Min Act: -0.1700
Data Index: 4573313 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.2901. Min Act: -0.1700
Data Index: 470384 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.2588. Min Act: -0.1700
Data Index: 8638738 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.2901. Min Act: -0.1700
Data Index: 6155303 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.2588. Min Act: -0.1700
Data Index: 5307832 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.2588. Min Act: -0.1700
Data Index: 7706496 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.2276. Min Act: -0.1700
Data Index: 3867522 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3838. Min Range: -7.3838
Max Act: 6.2276. Min Act: -0.1700
Data Index: 6888956 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19