Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5142 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4599. Min Range: -5.4599
Max Act: 5.4599. Min Act: -0.1700
Data Index: 6271907 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4599. Min Range: -5.4599
Max Act: 5.1474. Min Act: -0.1700
Data Index: 7806255 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4599. Min Range: -5.4599
Max Act: 5.1161. Min Act: -0.1700
Data Index: 4505259 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4599. Min Range: -5.4599
Max Act: 5.1161. Min Act: -0.1700
Data Index: 3938683 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4599. Min Range: -5.4599
Max Act: 5.0849. Min Act: -0.1700
Data Index: 5281514 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4599. Min Range: -5.4599
Max Act: 5.0536. Min Act: -0.1700
Data Index: 3713722 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4599. Min Range: -5.4599
Max Act: 5.0536. Min Act: -0.1700
Data Index: 6360538 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4599. Min Range: -5.4599
Max Act: 5.0849. Min Act: -0.1700
Data Index: 6870474 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4599. Min Range: -5.4599
Max Act: 5.0224. Min Act: -0.1700
Data Index: 1901461 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4599. Min Range: -5.4599
Max Act: 5.0224. Min Act: -0.1700
Data Index: 2785607 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4599. Min Range: -5.4599
Max Act: 4.9911. Min Act: -0.1700
Data Index: 5393667 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4599. Min Range: -5.4599
Max Act: 4.9911. Min Act: -0.1700
Data Index: 8239106 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4599. Min Range: -5.4599
Max Act: 4.9911. Min Act: -0.1699
Data Index: 2976114 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4599. Min Range: -5.4599
Max Act: 4.9911. Min Act: -0.1700
Data Index: 6000096 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4599. Min Range: -5.4599
Max Act: 4.9911. Min Act: -0.1700
Data Index: 7568141 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4599. Min Range: -5.4599
Max Act: 4.9599. Min Act: -0.1700
Data Index: 1996674 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4599. Min Range: -5.4599
Max Act: 4.9599. Min Act: -0.1700
Data Index: 4432852 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4599. Min Range: -5.4599
Max Act: 4.9286. Min Act: -0.1700
Data Index: 755326 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4599. Min Range: -5.4599
Max Act: 4.9286. Min Act: -0.1700
Data Index: 2405239 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4599. Min Range: -5.4599
Max Act: 4.9599. Min Act: -0.1700
Data Index: 3685412 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19