Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.8322. Min Act: -0.1700
Data Index: 7824676 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.7685. Min Act: -0.1700
Data Index: 5315516 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.7206. Min Act: -0.1700
Data Index: 5082135 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.6726. Min Act: -0.1700
Data Index: 5315521 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.6083. Min Act: -0.1700
Data Index: 1730593 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5922. Min Act: -0.1700
Data Index: 3047181 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5922. Min Act: -0.1700
Data Index: 3511692 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.6083. Min Act: -0.1700
Data Index: 5173046 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.6083. Min Act: -0.1700
Data Index: 2731971 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5761. Min Act: -0.1700
Data Index: 4461074 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5761. Min Act: -0.1700
Data Index: 641901 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5761. Min Act: -0.1700
Data Index: 234353 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5439. Min Act: -0.1700
Data Index: 1692253 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5439. Min Act: -0.1700
Data Index: 301406 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5439. Min Act: -0.1700
Data Index: 6944836 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5115. Min Act: -0.1700
Data Index: 981661 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5277. Min Act: -0.1700
Data Index: 2759052 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5115. Min Act: -0.1700
Data Index: 1824839 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5115. Min Act: -0.1700
Data Index: 3497509 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8322. Min Range: -2.8322
Max Act: 2.5115. Min Act: -0.1700
Data Index: 5847572 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19