Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0894. Min Range: -7.0894
Max Act: 7.0894. Min Act: -0.1700
Data Index: 8327787 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0894. Min Range: -7.0894
Max Act: 7.0581. Min Act: -0.1700
Data Index: 2823593 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.9956. Min Act: -0.1700
Data Index: 7940940 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.9331. Min Act: -0.1700
Data Index: 7733862 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.8706. Min Act: -0.1700
Data Index: 4616797 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.8706. Min Act: -0.1700
Data Index: 4223905 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.8081. Min Act: -0.1700
Data Index: 5541403 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.7769. Min Act: -0.1700
Data Index: 5023335 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.7456. Min Act: -0.1700
Data Index: 3322167 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.7456. Min Act: -0.1700
Data Index: 6871567 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.7456. Min Act: -0.1700
Data Index: 360355 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.7456. Min Act: -0.1700
Data Index: 7894350 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.7456. Min Act: -0.1700
Data Index: 1307257 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.6831. Min Act: -0.1700
Data Index: 5992828 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.7144. Min Act: -0.1700
Data Index: 4441267 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.7144. Min Act: -0.1700
Data Index: 7430666 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.6831. Min Act: -0.1700
Data Index: 8306739 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.6519. Min Act: -0.1700
Data Index: 381045 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.6206. Min Act: -0.1700
Data Index: 6598555 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0894. Min Range: -7.0894
Max Act: 6.6519. Min Act: -0.1700
Data Index: 1001015 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19