Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1773 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.9503. Min Act: -0.1700
Data Index: 3294329 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7939. Min Act: -0.1700
Data Index: 7320296 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.7001. Min Act: -0.1700
Data Index: 1812855 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.6531. Min Act: -0.1700
Data Index: 6535023 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.6062. Min Act: -0.1700
Data Index: 6514702 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5592. Min Act: -0.1700
Data Index: 692959 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5279. Min Act: -0.1700
Data Index: 6188430 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 8101097 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 7504678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 3222267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 8349583 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 2700274 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 938400 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 3904374 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 2173013 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 3398575 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 805940 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.5123. Min Act: -0.1700
Data Index: 3911616 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.4809. Min Act: -0.1700
Data Index: 3605623 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9503. Min Range: -3.9503
Max Act: 3.4809. Min Act: -0.1700
Data Index: 7599785 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19