Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6475. Min Range: -11.6475
Max Act: 11.6475. Min Act: -0.1700
Data Index: 6606842 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6475. Min Range: -11.6475
Max Act: 11.2725. Min Act: -0.1700
Data Index: 6196182 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.8350. Min Act: -0.1700
Data Index: 6820221 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.7100. Min Act: -0.1700
Data Index: 7602832 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.6475. Min Act: -0.1700
Data Index: 4294325 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.6475. Min Act: -0.1700
Data Index: 2581101 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.5850. Min Act: -0.1700
Data Index: 7612350 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.5225. Min Act: -0.1700
Data Index: 2356560 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.3975. Min Act: -0.1697
Data Index: 3982612 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.3975. Min Act: -0.1700
Data Index: 7164841 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.3350. Min Act: -0.1700
Data Index: 3754822 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.2725. Min Act: -0.1700
Data Index: 4875393 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.2725. Min Act: -0.1700
Data Index: 8165759 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.2100. Min Act: -0.1700
Data Index: 2866387 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.2100. Min Act: -0.1700
Data Index: 4663658 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.2100. Min Act: -0.1700
Data Index: 896000 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.0850. Min Act: -0.1700
Data Index: 1389026 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.1475. Min Act: -0.1700
Data Index: 1242840 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.0850. Min Act: -0.1700
Data Index: 5153906 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6475. Min Range: -11.6475
Max Act: 10.0850. Min Act: -0.1700
Data Index: 1908056 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19