Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1201 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.6389. Min Act: -0.1700
Data Index: 3697559 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.6076. Min Act: -0.1700
Data Index: 2612139 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.6389. Min Act: -0.1700
Data Index: 4008416 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.6076. Min Act: -0.1700
Data Index: 887982 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.5451. Min Act: -0.1700
Data Index: 406112 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.5451. Min Act: -0.1700
Data Index: 720149 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.5451. Min Act: -0.1700
Data Index: 3701728 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.5451. Min Act: -0.1700
Data Index: 3713774 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.5139. Min Act: -0.1700
Data Index: 8772288 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.5139. Min Act: -0.1700
Data Index: 217692 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.5139. Min Act: -0.1700
Data Index: 1214258 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.4826. Min Act: -0.1700
Data Index: 3209629 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.4826. Min Act: -0.1700
Data Index: 8809122 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.4514. Min Act: -0.1700
Data Index: 1997930 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.4514. Min Act: -0.1700
Data Index: 4049323 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.4201. Min Act: -0.1700
Data Index: 4281371 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.4514. Min Act: -0.1700
Data Index: 8142659 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.4514. Min Act: -0.1700
Data Index: 3787698 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.4514. Min Act: -0.1700
Data Index: 3573544 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6389. Min Range: -5.6389
Max Act: 5.4514. Min Act: -0.1700
Data Index: 1274000 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19