Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 965 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.5010. Min Act: -0.1700
Data Index: 1746414 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.2510. Min Act: -0.1700
Data Index: 4272253 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.2197. Min Act: -0.1700
Data Index: 1723289 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0947. Min Act: -0.1700
Data Index: 5888318 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0635. Min Act: -0.1700
Data Index: 5878585 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0322. Min Act: -0.1700
Data Index: 843591 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0635. Min Act: -0.1700
Data Index: 1108814 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0322. Min Act: -0.1700
Data Index: 8787470 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0322. Min Act: -0.1700
Data Index: 5052188 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0010. Min Act: -0.1700
Data Index: 7148573 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0010. Min Act: -0.1700
Data Index: 3802790 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0010. Min Act: -0.1700
Data Index: 5523917 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0010. Min Act: -0.1700
Data Index: 7551361 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5010. Min Range: -6.5010
Max Act: 6.0322. Min Act: -0.1700
Data Index: 1637266 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5010. Min Range: -6.5010
Max Act: 5.9697. Min Act: -0.1700
Data Index: 4970780 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5010. Min Range: -6.5010
Max Act: 5.9697. Min Act: -0.1700
Data Index: 4172672 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5010. Min Range: -6.5010
Max Act: 5.9072. Min Act: -0.1700
Data Index: 1236942 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5010. Min Range: -6.5010
Max Act: 5.9072. Min Act: -0.1700
Data Index: 3117761 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5010. Min Range: -6.5010
Max Act: 5.8760. Min Act: -0.1700
Data Index: 1789892 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5010. Min Range: -6.5010
Max Act: 5.8760. Min Act: -0.1700
Data Index: 2265122 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19