Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.5834. Min Act: -0.1700
Data Index: 7712551 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.3954. Min Act: -0.1700
Data Index: 663528 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.3640. Min Act: -0.1700
Data Index: 3975354 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.2542. Min Act: -0.1700
Data Index: 1684630 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.2542. Min Act: -0.1700
Data Index: 5075569 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.2856. Min Act: -0.1700
Data Index: 3257650 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.2385. Min Act: -0.1700
Data Index: 4252389 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.2385. Min Act: -0.1700
Data Index: 6400167 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.2542. Min Act: -0.1700
Data Index: 1214642 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.2070. Min Act: -0.1700
Data Index: 3389774 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.1756. Min Act: -0.1700
Data Index: 2907625 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.2070. Min Act: -0.1700
Data Index: 7889057 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.1913. Min Act: -0.1700
Data Index: 6127495 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.1756. Min Act: -0.1700
Data Index: 471360 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.1756. Min Act: -0.1700
Data Index: 4351884 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.1756. Min Act: -0.1700
Data Index: 3164663 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.1441. Min Act: -0.1700
Data Index: 748237 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.1598. Min Act: -0.1700
Data Index: 1777800 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.1126. Min Act: -0.1700
Data Index: 1413566 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5834. Min Range: -3.5834
Max Act: 3.1126. Min Act: -0.1700
Data Index: 1673164 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19