Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2819 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.8910. Min Act: -0.1700
Data Index: 5725583 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.8285. Min Act: -0.1700
Data Index: 2714523 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.7035. Min Act: -0.1700
Data Index: 583850 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.5472. Min Act: -0.1700
Data Index: 7321325 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.5785. Min Act: -0.1700
Data Index: 5046656 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.5160. Min Act: -0.1700
Data Index: 6744837 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.5160. Min Act: -0.1700
Data Index: 846816 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4847. Min Act: -0.1700
Data Index: 7920667 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4847. Min Act: -0.1700
Data Index: 7681374 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4535. Min Act: -0.1700
Data Index: 7526994 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4222. Min Act: -0.1700
Data Index: 963506 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4222. Min Act: -0.1700
Data Index: 3897801 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4222. Min Act: -0.1700
Data Index: 7681376 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3910. Min Act: -0.1700
Data Index: 1692677 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3910. Min Act: -0.1700
Data Index: 7892164 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3910. Min Act: -0.1700
Data Index: 6644628 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.4222. Min Act: -0.1700
Data Index: 84053 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3285. Min Act: -0.1700
Data Index: 5640712 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.3285. Min Act: -0.1700
Data Index: 7475015 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8910. Min Range: -5.8910
Max Act: 5.2660. Min Act: -0.1700
Data Index: 4473862 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19