Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 771 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.8651. Min Act: -0.1700
Data Index: 6806661 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.6464. Min Act: -0.1700
Data Index: 4189854 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.5839. Min Act: -0.1700
Data Index: 663726 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.5526. Min Act: -0.1700
Data Index: 4135870 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.5214. Min Act: -0.1700
Data Index: 6931272 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.5214. Min Act: -0.1700
Data Index: 4741089 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.4589. Min Act: -0.1700
Data Index: 8007921 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.4276. Min Act: -0.1700
Data Index: 3534030 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.4276. Min Act: -0.1700
Data Index: 3611691 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.4276. Min Act: -0.1700
Data Index: 8474284 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.3964. Min Act: -0.1700
Data Index: 5266004 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.3964. Min Act: -0.1700
Data Index: 7685439 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.3964. Min Act: -0.1700
Data Index: 234231 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.3964. Min Act: -0.1700
Data Index: 8578198 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.3964. Min Act: -0.1700
Data Index: 5102981 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.3651. Min Act: -0.1700
Data Index: 8568625 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.3651. Min Act: -0.1700
Data Index: 4155362 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.3651. Min Act: -0.1700
Data Index: 1737742 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.3339. Min Act: -0.1700
Data Index: 7839892 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8651. Min Range: -4.8651
Max Act: 4.3339. Min Act: -0.1700
Data Index: 4887280 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19