Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.8952. Min Act: -0.1700
Data Index: 5303037 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.6140. Min Act: -0.1700
Data Index: 7390555 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.4890. Min Act: -0.1700
Data Index: 997779 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.3952. Min Act: -0.1700
Data Index: 8291974 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.3640. Min Act: -0.1700
Data Index: 3541627 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.3640. Min Act: -0.1700
Data Index: 1047126 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.3015. Min Act: -0.1700
Data Index: 2037351 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.3015. Min Act: -0.1700
Data Index: 2819580 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.2702. Min Act: -0.1700
Data Index: 1318090 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.2077. Min Act: -0.1700
Data Index: 1827695 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.2077. Min Act: -0.1700
Data Index: 5037464 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.2077. Min Act: -0.1700
Data Index: 1232861 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.2077. Min Act: -0.1700
Data Index: 7395416 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.1765. Min Act: -0.1700
Data Index: 3921419 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.1140. Min Act: -0.1700
Data Index: 7947006 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.1452. Min Act: -0.1700
Data Index: 6420267 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.1140. Min Act: -0.1700
Data Index: 1047129 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.0515. Min Act: -0.1700
Data Index: 1579550 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.0515. Min Act: -0.1700
Data Index: 5563202 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8952. Min Range: -7.8952
Max Act: 7.0827. Min Act: -0.1700
Data Index: 4812882 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19