Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1490 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.6338. Min Act: -0.1700
Data Index: 61094 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.5639. Min Act: -0.1700
Data Index: 6469827 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.5464. Min Act: -0.1699
Data Index: 231233 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.5289. Min Act: -0.1699
Data Index: 6992083 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.5114. Min Act: -0.1700
Data Index: 2299179 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.5114. Min Act: -0.1700
Data Index: 4968213 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4762. Min Act: -0.1700
Data Index: 4208449 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4938. Min Act: -0.1700
Data Index: 1405305 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4938. Min Act: -0.1699
Data Index: 4737945 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4938. Min Act: -0.1700
Data Index: 4695612 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4762. Min Act: -0.1700
Data Index: 3506421 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4938. Min Act: -0.1695
Data Index: 4237869 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4762. Min Act: -0.1699
Data Index: 2521303 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4762. Min Act: -0.1700
Data Index: 3585563 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4762. Min Act: -0.1700
Data Index: 4980888 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4587. Min Act: -0.1700
Data Index: 76050 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4587. Min Act: -0.1700
Data Index: 3531799 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4587. Min Act: -0.1700
Data Index: 4307662 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4587. Min Act: -0.1699
Data Index: 4254297 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6338. Min Range: -1.6338
Max Act: 1.4587. Min Act: -0.1700
Data Index: 3812455 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19