Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1072 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0311. Min Range: -9.0311
Max Act: 9.0311. Min Act: -0.1700
Data Index: 1612991 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.6561. Min Act: -0.1700
Data Index: 3268530 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.6561. Min Act: -0.1700
Data Index: 6076282 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.5311. Min Act: -0.1700
Data Index: 6571642 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.5311. Min Act: -0.1700
Data Index: 1956454 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.4686. Min Act: -0.1700
Data Index: 2461684 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.4061. Min Act: -0.1700
Data Index: 1585434 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.4061. Min Act: -0.1700
Data Index: 5743702 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.3436. Min Act: -0.1700
Data Index: 6333207 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.3436. Min Act: -0.1700
Data Index: 5394378 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.2811. Min Act: -0.1700
Data Index: 5933628 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.2811. Min Act: -0.1700
Data Index: 3009346 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.2811. Min Act: -0.1700
Data Index: 712360 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.2811. Min Act: -0.1700
Data Index: 526858 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.2186. Min Act: -0.1700
Data Index: 6314032 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.2186. Min Act: -0.1700
Data Index: 8131629 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.2186. Min Act: -0.1700
Data Index: 3483798 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.1561. Min Act: -0.1700
Data Index: 5469443 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.1561. Min Act: -0.1700
Data Index: 6480399 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0311. Min Range: -9.0311
Max Act: 8.0623. Min Act: -0.1700
Data Index: 4856239 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19