Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5252 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2649. Min Range: -7.2649
Max Act: 7.2649. Min Act: -0.1700
Data Index: 4158572 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.9837. Min Act: -0.1700
Data Index: 4040202 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.9524. Min Act: -0.1700
Data Index: 1190168 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.8274. Min Act: -0.1700
Data Index: 5502577 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.7962. Min Act: -0.1700
Data Index: 5902549 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.7649. Min Act: -0.1700
Data Index: 5921938 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.7649. Min Act: -0.1700
Data Index: 6027267 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.7337. Min Act: -0.1700
Data Index: 25107 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.7337. Min Act: -0.1700
Data Index: 2625215 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.7024. Min Act: -0.1700
Data Index: 611355 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.7024. Min Act: -0.1700
Data Index: 1613343 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.7024. Min Act: -0.1700
Data Index: 7759092 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.6712. Min Act: -0.1700
Data Index: 3779201 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.7337. Min Act: -0.1700
Data Index: 6830197 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.6712. Min Act: -0.1700
Data Index: 3479190 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.7024. Min Act: -0.1700
Data Index: 8708045 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.6399. Min Act: -0.1700
Data Index: 282071 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.6399. Min Act: -0.1700
Data Index: 5031083 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.6087. Min Act: -0.1700
Data Index: 3058392 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2649. Min Range: -7.2649
Max Act: 6.6399. Min Act: -0.1700
Data Index: 5061606 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19