Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1554 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.7487. Min Act: -0.1700
Data Index: 4122543 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6967. Min Act: -0.1668
Data Index: 2596636 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6794. Min Act: -0.1700
Data Index: 5088778 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6620. Min Act: -0.1700
Data Index: 6395852 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6620. Min Act: -0.1700
Data Index: 2986953 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6794. Min Act: -0.1699
Data Index: 7354317 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6794. Min Act: -0.1700
Data Index: 6504738 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6533. Min Act: -0.1700
Data Index: 8107440 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6533. Min Act: -0.1700
Data Index: 7309647 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6620. Min Act: -0.1698
Data Index: 942261 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6620. Min Act: -0.1700
Data Index: 3931280 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6707. Min Act: -0.1700
Data Index: 4525477 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6446. Min Act: -0.1699
Data Index: 2490085 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6533. Min Act: -0.1700
Data Index: 146266 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6533. Min Act: -0.1699
Data Index: 4341826 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6446. Min Act: -0.1700
Data Index: 2099352 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6533. Min Act: -0.1700
Data Index: 3493338 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6533. Min Act: -0.1700
Data Index: 1156737 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6446. Min Act: -0.1700
Data Index: 1483051 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7487. Min Range: -1.7487
Max Act: 1.6359. Min Act: -0.1700
Data Index: 5346106 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19