Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3694 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.8360. Min Act: -0.1700
Data Index: 447316 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.7110. Min Act: -0.1700
Data Index: 4928423 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.6797. Min Act: -0.1700
Data Index: 3915107 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.6797. Min Act: -0.1700
Data Index: 8275548 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.6485. Min Act: -0.1700
Data Index: 1167925 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5860. Min Act: -0.1700
Data Index: 4663620 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5860. Min Act: -0.1700
Data Index: 7723080 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5860. Min Act: -0.1700
Data Index: 7939639 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.6172. Min Act: -0.1700
Data Index: 5097966 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1386485 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5547. Min Act: -0.1700
Data Index: 7060473 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5547. Min Act: -0.1700
Data Index: 479192 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5235. Min Act: -0.1700
Data Index: 140156 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5235. Min Act: -0.1700
Data Index: 3193051 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5235. Min Act: -0.1700
Data Index: 1438796 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5235. Min Act: -0.1700
Data Index: 1563135 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5235. Min Act: -0.1700
Data Index: 4291235 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5547. Min Act: -0.1700
Data Index: 3113944 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5235. Min Act: -0.1700
Data Index: 3455936 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8360. Min Range: -4.8360
Max Act: 4.5235. Min Act: -0.1700
Data Index: 5536270 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19