Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1479 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.9282. Min Act: -0.1700
Data Index: 4386103 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.8032. Min Act: -0.1700
Data Index: 3102553 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.7407. Min Act: -0.1700
Data Index: 4084651 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.7407. Min Act: -0.1700
Data Index: 7311123 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.6157. Min Act: -0.1700
Data Index: 3182936 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.6157. Min Act: -0.1700
Data Index: 1426446 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.6157. Min Act: -0.1700
Data Index: 8440025 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.5532. Min Act: -0.1700
Data Index: 7607002 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.4907. Min Act: -0.1700
Data Index: 6425843 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.5532. Min Act: -0.1700
Data Index: 3005920 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.5532. Min Act: -0.1700
Data Index: 2028388 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.4907. Min Act: -0.1700
Data Index: 5936145 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.4907. Min Act: -0.1700
Data Index: 6464863 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.4907. Min Act: -0.1700
Data Index: 3635317 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.4907. Min Act: -0.1700
Data Index: 8797559 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.4907. Min Act: -0.1700
Data Index: 7451234 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.4282. Min Act: -0.1700
Data Index: 8788026 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.4282. Min Act: -0.1700
Data Index: 8663282 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.3032. Min Act: -0.1700
Data Index: 6855930 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9282. Min Range: -8.9282
Max Act: 8.3657. Min Act: -0.1700
Data Index: 5919371 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19