Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0100. Min Range: -4.0100
Max Act: 4.0100. Min Act: -0.1700
Data Index: 3451797 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.9787. Min Act: -0.1700
Data Index: 8130404 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.9162. Min Act: -0.1700
Data Index: 2108952 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.8849. Min Act: -0.1700
Data Index: 4883904 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.8849. Min Act: -0.1700
Data Index: 816712 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.8849. Min Act: -0.1700
Data Index: 2421940 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7911. Min Act: -0.1700
Data Index: 1918556 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.8068. Min Act: -0.1700
Data Index: 6274554 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.8068. Min Act: -0.1700
Data Index: 2778267 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7755. Min Act: -0.1700
Data Index: 8233433 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7911. Min Act: -0.1700
Data Index: 1534284 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7598. Min Act: -0.1700
Data Index: 515222 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7598. Min Act: -0.1700
Data Index: 3675032 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7442. Min Act: -0.1700
Data Index: 4558639 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7286. Min Act: -0.1700
Data Index: 4425785 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7286. Min Act: -0.1700
Data Index: 7365367 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7286. Min Act: -0.1700
Data Index: 5474439 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7442. Min Act: -0.1700
Data Index: 4970479 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.7129. Min Act: -0.1700
Data Index: 913792 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0100. Min Range: -4.0100
Max Act: 3.6973. Min Act: -0.1700
Data Index: 578820 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19