Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.7581. Min Act: -0.1700
Data Index: 2819262 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.6331. Min Act: -0.1700
Data Index: 4025709 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.5394. Min Act: -0.1700
Data Index: 8490121 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.4456. Min Act: -0.1700
Data Index: 817335 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.4456. Min Act: -0.1700
Data Index: 3436888 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.3519. Min Act: -0.1700
Data Index: 533156 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.3519. Min Act: -0.1700
Data Index: 416531 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.3519. Min Act: -0.1700
Data Index: 5248303 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.3519. Min Act: -0.1700
Data Index: 7380545 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.3206. Min Act: -0.1700
Data Index: 930553 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.3206. Min Act: -0.1700
Data Index: 5716633 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.3206. Min Act: -0.1700
Data Index: 5346659 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.3206. Min Act: -0.1700
Data Index: 2910709 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.3206. Min Act: -0.1700
Data Index: 5256180 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.2581. Min Act: -0.1700
Data Index: 5609835 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.2894. Min Act: -0.1700
Data Index: 6037427 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.2581. Min Act: -0.1700
Data Index: 2963530 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.1956. Min Act: -0.1700
Data Index: 8199504 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.2269. Min Act: -0.1700
Data Index: 4653550 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7581. Min Range: -6.7581
Max Act: 6.1956. Min Act: -0.1700
Data Index: 6181509 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19