Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5477 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.8221. Min Act: -0.1700
Data Index: 6683096 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.7909. Min Act: -0.1700
Data Index: 4552431 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.6659. Min Act: -0.1700
Data Index: 2790398 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.4784. Min Act: -0.1700
Data Index: 2963282 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.4159. Min Act: -0.1700
Data Index: 4661376 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.3534. Min Act: -0.1700
Data Index: 7024811 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.3534. Min Act: -0.1700
Data Index: 8303875 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.3221. Min Act: -0.1700
Data Index: 6949365 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.3221. Min Act: -0.1700
Data Index: 4767638 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.2284. Min Act: -0.1700
Data Index: 6234983 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.2284. Min Act: -0.1700
Data Index: 6747583 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.1971. Min Act: -0.1700
Data Index: 453199 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.2284. Min Act: -0.1700
Data Index: 5466574 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.2284. Min Act: -0.1700
Data Index: 5600989 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.1971. Min Act: -0.1700
Data Index: 1224687 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.1659. Min Act: -0.1700
Data Index: 8750367 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.1034. Min Act: -0.1700
Data Index: 2491222 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.1034. Min Act: -0.1700
Data Index: 3176374 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.1034. Min Act: -0.1700
Data Index: 4846114 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8221. Min Range: -6.8221
Max Act: 6.0721. Min Act: -0.1700
Data Index: 8022360 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19