Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4453 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9131. Min Range: -11.9131
Max Act: 11.9131. Min Act: -0.1700
Data Index: 8381431 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9131. Min Range: -11.9131
Max Act: 11.7256. Min Act: -0.1700
Data Index: 8397024 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9131. Min Range: -11.9131
Max Act: 11.4756. Min Act: -0.1700
Data Index: 4185810 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9131. Min Range: -11.9131
Max Act: 11.1631. Min Act: -0.1700
Data Index: 3310887 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9131. Min Range: -11.9131
Max Act: 11.2256. Min Act: -0.1700
Data Index: 6327686 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9131. Min Range: -11.9131
Max Act: 11.1631. Min Act: -0.1700
Data Index: 1923242 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9131. Min Range: -11.9131
Max Act: 11.1631. Min Act: -0.1700
Data Index: 3050806 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9131. Min Range: -11.9131
Max Act: 11.1006. Min Act: -0.1700
Data Index: 5996628 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.9131. Min Act: -0.1700
Data Index: 2219761 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.7256. Min Act: -0.1700
Data Index: 6820262 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.7256. Min Act: -0.1700
Data Index: 7257536 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.6631. Min Act: -0.1700
Data Index: 2755433 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.6631. Min Act: -0.1700
Data Index: 629234 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.6006. Min Act: -0.1700
Data Index: 4016523 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.6631. Min Act: -0.1700
Data Index: 5983109 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.5381. Min Act: -0.1700
Data Index: 6614902 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.5381. Min Act: -0.1700
Data Index: 96797 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.5381. Min Act: -0.1700
Data Index: 2724046 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.4756. Min Act: -0.1700
Data Index: 4849 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9131. Min Range: -11.9131
Max Act: 10.4756. Min Act: -0.1700
Data Index: 1282556 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19