Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.8238. Min Act: -0.1700
Data Index: 3826812 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.6988. Min Act: -0.1700
Data Index: 7571925 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.6988. Min Act: -0.1700
Data Index: 5023589 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.6676. Min Act: -0.1700
Data Index: 1013607 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.5738. Min Act: -0.1700
Data Index: 742409 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.5738. Min Act: -0.1700
Data Index: 6329577 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.5738. Min Act: -0.1700
Data Index: 8314170 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.5426. Min Act: -0.1700
Data Index: 4304351 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.5113. Min Act: -0.1700
Data Index: 4782536 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.5113. Min Act: -0.1700
Data Index: 5071199 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.5113. Min Act: -0.1700
Data Index: 4877250 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.4488. Min Act: -0.1700
Data Index: 1398355 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.4488. Min Act: -0.1700
Data Index: 305067 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.4176. Min Act: -0.1700
Data Index: 7352745 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.4176. Min Act: -0.1700
Data Index: 4826542 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.4176. Min Act: -0.1700
Data Index: 3609857 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.4176. Min Act: -0.1700
Data Index: 1344533 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.3863. Min Act: -0.1700
Data Index: 1037521 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.3863. Min Act: -0.1700
Data Index: 6287270 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8238. Min Range: -5.8238
Max Act: 5.3551. Min Act: -0.1700
Data Index: 8364410 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19