Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2690 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0617. Min Range: -3.0617
Max Act: 3.0459. Min Act: -0.1700
Data Index: 3112968 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0617. Min Range: -3.0617
Max Act: 3.0617. Min Act: -0.1700
Data Index: 3589294 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0617. Min Range: -3.0617
Max Act: 3.0144. Min Act: -0.1700
Data Index: 489358 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9986. Min Act: -0.1700
Data Index: 999047 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9986. Min Act: -0.1700
Data Index: 596965 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9986. Min Act: -0.1700
Data Index: 7687316 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9669. Min Act: -0.1700
Data Index: 7159273 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9669. Min Act: -0.1700
Data Index: 8232272 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9511. Min Act: -0.1700
Data Index: 5048482 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9511. Min Act: -0.1700
Data Index: 6698765 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9669. Min Act: -0.1700
Data Index: 4728517 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9511. Min Act: -0.1700
Data Index: 7279465 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9353. Min Act: -0.1700
Data Index: 5048483 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9353. Min Act: -0.1700
Data Index: 4728519 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9194. Min Act: -0.1700
Data Index: 1198753 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9036. Min Act: -0.1700
Data Index: 3150364 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9194. Min Act: -0.1700
Data Index: 7275926 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9036. Min Act: -0.1700
Data Index: 6131416 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9036. Min Act: -0.1700
Data Index: 7144698 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0617. Min Range: -3.0617
Max Act: 2.9036. Min Act: -0.1700
Data Index: 3458739 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19