Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2233 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2809. Min Range: -6.2809
Max Act: 6.2809. Min Act: -0.1700
Data Index: 3940935 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2809. Min Range: -6.2809
Max Act: 6.1559. Min Act: -0.1700
Data Index: 6578307 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2809. Min Range: -6.2809
Max Act: 6.0309. Min Act: -0.1700
Data Index: 8111077 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.9684. Min Act: -0.1700
Data Index: 330100 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.8746. Min Act: -0.1700
Data Index: 3458104 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.8434. Min Act: -0.1700
Data Index: 5156296 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.8746. Min Act: -0.1700
Data Index: 4993347 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.8746. Min Act: -0.1700
Data Index: 14827 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.8434. Min Act: -0.1700
Data Index: 3426449 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.8434. Min Act: -0.1700
Data Index: 2045255 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.8121. Min Act: -0.1700
Data Index: 4878492 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.7809. Min Act: -0.1700
Data Index: 264556 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.7809. Min Act: -0.1700
Data Index: 2160072 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.7496. Min Act: -0.1700
Data Index: 8712237 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.7184. Min Act: -0.1700
Data Index: 2167649 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.7184. Min Act: -0.1700
Data Index: 7976920 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.7184. Min Act: -0.1700
Data Index: 7782921 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.6871. Min Act: -0.1700
Data Index: 7056544 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.7184. Min Act: -0.1700
Data Index: 5099754 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2809. Min Range: -6.2809
Max Act: 5.6871. Min Act: -0.1700
Data Index: 6231340 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19