Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4173 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.9388. Min Act: -0.1700
Data Index: 6986011 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.7825. Min Act: -0.1700
Data Index: 4825194 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.7825. Min Act: -0.1700
Data Index: 6348942 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6888. Min Act: -0.1700
Data Index: 3076287 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6888. Min Act: -0.1700
Data Index: 6175406 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6575. Min Act: -0.1700
Data Index: 4830395 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6263. Min Act: -0.1700
Data Index: 458934 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6263. Min Act: -0.1700
Data Index: 6043218 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.6263. Min Act: -0.1700
Data Index: 6434095 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5950. Min Act: -0.1700
Data Index: 2065651 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5638. Min Act: -0.1700
Data Index: 2901023 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5638. Min Act: -0.1700
Data Index: 1697136 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5013. Min Act: -0.1700
Data Index: 163985 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5013. Min Act: -0.1700
Data Index: 7411344 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.4700. Min Act: -0.1700
Data Index: 4359620 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.5013. Min Act: -0.1700
Data Index: 5080872 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.4700. Min Act: -0.1700
Data Index: 4006387 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.4388. Min Act: -0.1700
Data Index: 5176406 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.4700. Min Act: -0.1700
Data Index: 112369 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9388. Min Range: -4.9388
Max Act: 4.4388. Min Act: -0.1700
Data Index: 5779222 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19