Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4484 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.8564. Min Act: -0.1700
Data Index: 3425300 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.8251. Min Act: -0.1700
Data Index: 3720365 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.8251. Min Act: -0.1700
Data Index: 3262892 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.8251. Min Act: -0.1700
Data Index: 4554578 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.8251. Min Act: -0.1700
Data Index: 8829776 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.8251. Min Act: -0.1700
Data Index: 1280627 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.8251. Min Act: -0.1700
Data Index: 3025438 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.7938. Min Act: -0.1700
Data Index: 626202 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.7626. Min Act: -0.1700
Data Index: 5413054 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.7626. Min Act: -0.1700
Data Index: 7438752 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.7626. Min Act: -0.1700
Data Index: 724322 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.7313. Min Act: -0.1700
Data Index: 5035347 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.7313. Min Act: -0.1700
Data Index: 5519092 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.7313. Min Act: -0.1700
Data Index: 7544443 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.7313. Min Act: -0.1700
Data Index: 4133588 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.7000. Min Act: -0.1700
Data Index: 7317405 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.6687. Min Act: -0.1700
Data Index: 398674 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.7000. Min Act: -0.1700
Data Index: 4300528 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.6687. Min Act: -0.1700
Data Index: 486450 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8564. Min Range: -3.8564
Max Act: 3.6687. Min Act: -0.1700
Data Index: 299620 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19