Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 698 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4526. Min Range: -9.4526
Max Act: 9.4526. Min Act: -0.1700
Data Index: 464303 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.5151. Min Act: -0.1700
Data Index: 4794410 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.3588. Min Act: -0.1700
Data Index: 742378 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.3276. Min Act: -0.1700
Data Index: 6409281 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.2651. Min Act: -0.1700
Data Index: 8794413 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.2338. Min Act: -0.1700
Data Index: 4794411 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.2026. Min Act: -0.1700
Data Index: 6356257 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.1713. Min Act: -0.1700
Data Index: 3825638 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.1713. Min Act: -0.1700
Data Index: 337356 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.1088. Min Act: -0.1700
Data Index: 701201 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.1088. Min Act: -0.1700
Data Index: 337341 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.0776. Min Act: -0.1700
Data Index: 953382 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.1088. Min Act: -0.1700
Data Index: 8640485 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.0776. Min Act: -0.1700
Data Index: 4794284 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.0776. Min Act: -0.1700
Data Index: 2529521 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.0463. Min Act: -0.1700
Data Index: 953389 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.0463. Min Act: -0.1700
Data Index: 337354 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.0776. Min Act: -0.1700
Data Index: 4188246 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4526. Min Range: -9.4526
Max Act: 8.0463. Min Act: -0.1700
Data Index: 2230765 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4526. Min Range: -9.4526
Max Act: 7.9838. Min Act: -0.1700
Data Index: 224303 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19