Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.3592. Min Act: -0.1700
Data Index: 7321645 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.2342. Min Act: -0.1700
Data Index: 4438657 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3592. Min Range: -5.3592
Max Act: 5.1405. Min Act: -0.1700
Data Index: 4438663 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.9530. Min Act: -0.1700
Data Index: 6244798 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.9217. Min Act: -0.1700
Data Index: 2219273 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.9217. Min Act: -0.1700
Data Index: 1155940 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.8592. Min Act: -0.1700
Data Index: 4934354 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.8905. Min Act: -0.1700
Data Index: 2267308 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.8905. Min Act: -0.1700
Data Index: 4815728 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.8592. Min Act: -0.1700
Data Index: 6244800 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.8592. Min Act: -0.1700
Data Index: 8402373 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.8280. Min Act: -0.1700
Data Index: 2695743 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.8280. Min Act: -0.1700
Data Index: 4670966 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.8280. Min Act: -0.1700
Data Index: 4438656 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.8280. Min Act: -0.1700
Data Index: 1659912 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.8280. Min Act: -0.1700
Data Index: 4438661 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.7967. Min Act: -0.1700
Data Index: 7315043 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.7655. Min Act: -0.1700
Data Index: 2430410 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.7655. Min Act: -0.1700
Data Index: 2735844 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3592. Min Range: -5.3592
Max Act: 4.7655. Min Act: -0.1700
Data Index: 4074758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19