Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1354 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.6750. Min Act: -0.1700
Data Index: 4950953 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.5500. Min Act: -0.1700
Data Index: 4850025 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.5187. Min Act: -0.1700
Data Index: 6375609 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.4562. Min Act: -0.1700
Data Index: 2428302 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.4875. Min Act: -0.1700
Data Index: 2605745 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.4562. Min Act: -0.1700
Data Index: 3648949 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.4875. Min Act: -0.1700
Data Index: 6765581 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.4562. Min Act: -0.1700
Data Index: 8341327 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.4250. Min Act: -0.1700
Data Index: 554834 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.3937. Min Act: -0.1700
Data Index: 1346648 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.4250. Min Act: -0.1700
Data Index: 2339501 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.4250. Min Act: -0.1700
Data Index: 8160555 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.3312. Min Act: -0.1700
Data Index: 4838584 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.3625. Min Act: -0.1700
Data Index: 1018634 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.3312. Min Act: -0.1700
Data Index: 4983530 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.3000. Min Act: -0.1700
Data Index: 6927655 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.3312. Min Act: -0.1700
Data Index: 4350282 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.3312. Min Act: -0.1700
Data Index: 3245035 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.3625. Min Act: -0.1700
Data Index: 2927707 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6750. Min Range: -7.6750
Max Act: 7.3000. Min Act: -0.1700
Data Index: 5365809 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19