Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3976 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.2038. Min Act: -0.1700
Data Index: 4602065 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9850. Min Act: -0.1700
Data Index: 1636952 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.0163. Min Act: -0.1700
Data Index: 6406781 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9538. Min Act: -0.1700
Data Index: 3202093 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9538. Min Act: -0.1700
Data Index: 1409424 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9225. Min Act: -0.1700
Data Index: 419008 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.8913. Min Act: -0.1700
Data Index: 2084303 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.8913. Min Act: -0.1700
Data Index: 6379802 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.8600. Min Act: -0.1700
Data Index: 4091781 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.8600. Min Act: -0.1700
Data Index: 7324068 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.8288. Min Act: -0.1700
Data Index: 2502238 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.8288. Min Act: -0.1700
Data Index: 6698400 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.8600. Min Act: -0.1700
Data Index: 6912581 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.7975. Min Act: -0.1700
Data Index: 5615793 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.7663. Min Act: -0.1700
Data Index: 1622808 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.8288. Min Act: -0.1700
Data Index: 859155 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.7975. Min Act: -0.1700
Data Index: 5276711 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.7663. Min Act: -0.1700
Data Index: 7576929 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.7975. Min Act: -0.1700
Data Index: 1649622 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.7350. Min Act: -0.1700
Data Index: 2557829 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19