Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.2881. Min Act: -0.1700
Data Index: 6676907 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.2881. Min Act: -0.1700
Data Index: 6879063 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.3194. Min Act: -0.1700
Data Index: 5443083 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.2569. Min Act: -0.1700
Data Index: 5273243 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.1944. Min Act: -0.1700
Data Index: 2807242 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.1631. Min Act: -0.1700
Data Index: 752486 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.1631. Min Act: -0.1700
Data Index: 340350 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.1006. Min Act: -0.1700
Data Index: 284993 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.1006. Min Act: -0.1700
Data Index: 3029170 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.1006. Min Act: -0.1700
Data Index: 1563033 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.0694. Min Act: -0.1700
Data Index: 1710961 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.1006. Min Act: -0.1700
Data Index: 1097178 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.0694. Min Act: -0.1700
Data Index: 1025446 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.0694. Min Act: -0.1700
Data Index: 7038804 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.0381. Min Act: -0.1700
Data Index: 8169502 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.0069. Min Act: -0.1700
Data Index: 5415697 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.0381. Min Act: -0.1700
Data Index: 6307614 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.0381. Min Act: -0.1700
Data Index: 1516100 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.0069. Min Act: -0.1700
Data Index: 1694145 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3194. Min Range: -5.3194
Max Act: 5.0381. Min Act: -0.1700
Data Index: 998854 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19