Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1814 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1099. Min Range: -5.1099
Max Act: 5.1099. Min Act: -0.1700
Data Index: 2856773 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.6724. Min Act: -0.1700
Data Index: 1845400 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.6411. Min Act: -0.1700
Data Index: 5981441 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.5786. Min Act: -0.1700
Data Index: 8169389 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.5161. Min Act: -0.1700
Data Index: 6478495 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.5161. Min Act: -0.1700
Data Index: 125418 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.4536. Min Act: -0.1700
Data Index: 6201995 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.4536. Min Act: -0.1700
Data Index: 1601756 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.4224. Min Act: -0.1700
Data Index: 5728416 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.4224. Min Act: -0.1700
Data Index: 432369 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.3911. Min Act: -0.1700
Data Index: 125410 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.3599. Min Act: -0.1700
Data Index: 3212398 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.3911. Min Act: -0.1700
Data Index: 6808308 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.3599. Min Act: -0.1700
Data Index: 5575706 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.3286. Min Act: -0.1700
Data Index: 6342107 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.2973. Min Act: -0.1700
Data Index: 8646203 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.3286. Min Act: -0.1700
Data Index: 7526088 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.2973. Min Act: -0.1700
Data Index: 4592131 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.3286. Min Act: -0.1700
Data Index: 4705455 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.2973. Min Act: -0.1700
Data Index: 5218991 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19