Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1351. Min Range: -2.1351
Max Act: 2.1351. Min Act: -0.1700
Data Index: 6839577 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1351. Min Range: -2.1351
Max Act: 2.0513. Min Act: -0.1700
Data Index: 4064228 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1351. Min Range: -2.1351
Max Act: 2.0513. Min Act: -0.1695
Data Index: 589177 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1351. Min Range: -2.1351
Max Act: 2.0176. Min Act: -0.1700
Data Index: 7076097 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1351. Min Range: -2.1351
Max Act: 2.0176. Min Act: -0.1700
Data Index: 749225 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.9838. Min Act: -0.1700
Data Index: 6054671 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1351. Min Range: -2.1351
Max Act: 2.0007. Min Act: -0.1700
Data Index: 2029406 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.9838. Min Act: -0.1700
Data Index: 1863975 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.9329. Min Act: -0.1700
Data Index: 2932665 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.9159. Min Act: -0.1700
Data Index: 2442595 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.8903. Min Act: -0.1700
Data Index: 3975628 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.9159. Min Act: -0.1700
Data Index: 4268724 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.8988. Min Act: -0.1700
Data Index: 5711770 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.8818. Min Act: -0.1700
Data Index: 7446296 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.8988. Min Act: -0.1700
Data Index: 91800 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.8818. Min Act: -0.1700
Data Index: 7370347 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.8818. Min Act: -0.1700
Data Index: 208573 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.8475. Min Act: -0.1700
Data Index: 1243733 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.8475. Min Act: -0.1700
Data Index: 4257393 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1351. Min Range: -2.1351
Max Act: 1.8647. Min Act: -0.1700
Data Index: 6054666 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19