Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2702. Min Range: -6.2702
Max Act: 6.2702. Min Act: -0.1700
Data Index: 8632416 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2702. Min Range: -6.2702
Max Act: 6.0827. Min Act: -0.1700
Data Index: 4994363 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2702. Min Range: -6.2702
Max Act: 6.0202. Min Act: -0.1700
Data Index: 2478908 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.9577. Min Act: -0.1700
Data Index: 6600007 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.7389. Min Act: -0.1700
Data Index: 6315051 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.7702. Min Act: -0.1700
Data Index: 2985167 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.7389. Min Act: -0.1700
Data Index: 6293326 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.6452. Min Act: -0.1700
Data Index: 4209017 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.6764. Min Act: -0.1700
Data Index: 4292709 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.6764. Min Act: -0.1700
Data Index: 5114205 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.6139. Min Act: -0.1700
Data Index: 1938131 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.6452. Min Act: -0.1700
Data Index: 3184873 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.6139. Min Act: -0.1700
Data Index: 204737 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.6452. Min Act: -0.1700
Data Index: 56609 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.5827. Min Act: -0.1700
Data Index: 5015559 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.6139. Min Act: -0.1700
Data Index: 7626295 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.5514. Min Act: -0.1700
Data Index: 2609612 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.5202. Min Act: -0.1700
Data Index: 8204553 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.5514. Min Act: -0.1700
Data Index: 8272298 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2702. Min Range: -6.2702
Max Act: 5.5514. Min Act: -0.1700
Data Index: 5667530 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19