Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2309 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0331. Min Range: -2.0331
Max Act: 2.0331. Min Act: -0.1700
Data Index: 6988100 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0331. Min Range: -2.0331
Max Act: 2.0163. Min Act: -0.1700
Data Index: 7460000 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9994. Min Act: -0.1700
Data Index: 3493698 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9825. Min Act: -0.1700
Data Index: 4334992 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9825. Min Act: -0.1700
Data Index: 1927115 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9486. Min Act: -0.1700
Data Index: 8382368 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9655. Min Act: -0.1700
Data Index: 1908905 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9486. Min Act: -0.1700
Data Index: 7899874 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9486. Min Act: -0.1700
Data Index: 5441711 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9316. Min Act: -0.1700
Data Index: 3194725 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9316. Min Act: -0.1700
Data Index: 215237 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9316. Min Act: -0.1700
Data Index: 6606943 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9316. Min Act: -0.1699
Data Index: 6933508 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9316. Min Act: -0.1700
Data Index: 6228479 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9316. Min Act: -0.1700
Data Index: 3485966 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9316. Min Act: -0.1700
Data Index: 2900813 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9316. Min Act: -0.1700
Data Index: 6841971 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9316. Min Act: -0.1700
Data Index: 4844289 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9486. Min Act: -0.1699
Data Index: 4444172 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0331. Min Range: -2.0331
Max Act: 1.9316. Min Act: -0.1700
Data Index: 6862540 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19