Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1587 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2260. Min Range: -8.2260
Max Act: 8.2260. Min Act: -0.1700
Data Index: 3468576 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.9760. Min Act: -0.1700
Data Index: 4459675 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.9135. Min Act: -0.1700
Data Index: 254069 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.9135. Min Act: -0.1700
Data Index: 4412291 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.7260. Min Act: -0.1700
Data Index: 4954903 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.6635. Min Act: -0.1700
Data Index: 2695764 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.7260. Min Act: -0.1700
Data Index: 5661997 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.6635. Min Act: -0.1700
Data Index: 5135121 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.5073. Min Act: -0.1700
Data Index: 8672258 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.4448. Min Act: -0.1700
Data Index: 4839774 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.3823. Min Act: -0.1700
Data Index: 3475096 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.4135. Min Act: -0.1700
Data Index: 5039725 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.4448. Min Act: -0.1700
Data Index: 3348797 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.3823. Min Act: -0.1700
Data Index: 5556643 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.3510. Min Act: -0.1700
Data Index: 553805 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.3510. Min Act: -0.1700
Data Index: 6525585 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.3198. Min Act: -0.1700
Data Index: 5477881 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.2885. Min Act: -0.1700
Data Index: 7761423 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.2885. Min Act: -0.1700
Data Index: 2468025 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2260. Min Range: -8.2260
Max Act: 7.2573. Min Act: -0.1700
Data Index: 5102519 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19