Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4427 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.9099. Min Act: -0.1700
Data Index: 1832072 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.8161. Min Act: -0.1700
Data Index: 3813474 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.6286. Min Act: -0.1700
Data Index: 3942068 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.5974. Min Act: -0.1700
Data Index: 6548540 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.6286. Min Act: -0.1700
Data Index: 7138314 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.5661. Min Act: -0.1700
Data Index: 7703116 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.5349. Min Act: -0.1700
Data Index: 6358373 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.5349. Min Act: -0.1700
Data Index: 5801710 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.5036. Min Act: -0.1700
Data Index: 5953552 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.5036. Min Act: -0.1700
Data Index: 2185879 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.4411. Min Act: -0.1700
Data Index: 1203462 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.4724. Min Act: -0.1700
Data Index: 1810205 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.4099. Min Act: -0.1700
Data Index: 2155713 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.3786. Min Act: -0.1700
Data Index: 705572 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.3786. Min Act: -0.1700
Data Index: 1610298 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.3786. Min Act: -0.1700
Data Index: 2871771 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.3474. Min Act: -0.1700
Data Index: 6731744 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.3474. Min Act: -0.1700
Data Index: 5661820 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.3474. Min Act: -0.1700
Data Index: 6840388 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9099. Min Range: -7.9099
Max Act: 7.3161. Min Act: -0.1700
Data Index: 8497112 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19