Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2835 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.7503. Min Act: -0.1700
Data Index: 2786717 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.7190. Min Act: -0.1700
Data Index: 1256787 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.6565. Min Act: -0.1700
Data Index: 6259896 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.6565. Min Act: -0.1700
Data Index: 2976750 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.6877. Min Act: -0.1700
Data Index: 8518962 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.6565. Min Act: -0.1700
Data Index: 2957972 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5939. Min Act: -0.1700
Data Index: 5543067 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5939. Min Act: -0.1700
Data Index: 1119372 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5469. Min Act: -0.1700
Data Index: 7109630 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5626. Min Act: -0.1700
Data Index: 1579207 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5469. Min Act: -0.1700
Data Index: 860576 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5469. Min Act: -0.1700
Data Index: 4354115 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5312. Min Act: -0.1700
Data Index: 1221110 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5312. Min Act: -0.1700
Data Index: 5039418 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5312. Min Act: -0.1700
Data Index: 4924094 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5156. Min Act: -0.1700
Data Index: 6566865 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5312. Min Act: -0.1700
Data Index: 4281271 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5312. Min Act: -0.1700
Data Index: 8395753 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5312. Min Act: -0.1700
Data Index: 1069110 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7503. Min Range: -3.7503
Max Act: 3.5312. Min Act: -0.1700
Data Index: 3128798 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19