Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1828 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.2850. Min Range: -10.2850
Max Act: 10.2850. Min Act: -0.1700
Data Index: 7135468 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.9725. Min Act: -0.1700
Data Index: 7238182 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.9100. Min Act: -0.1700
Data Index: 8334237 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.7225. Min Act: -0.1700
Data Index: 5316545 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.5975. Min Act: -0.1700
Data Index: 3275862 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.6600. Min Act: -0.1700
Data Index: 8130493 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.5350. Min Act: -0.1700
Data Index: 4552512 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.5350. Min Act: -0.1700
Data Index: 7326676 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.5975. Min Act: -0.1700
Data Index: 8566890 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.4725. Min Act: -0.1700
Data Index: 6792380 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.4100. Min Act: -0.1700
Data Index: 4105579 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.4725. Min Act: -0.1700
Data Index: 7732906 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.4100. Min Act: -0.1700
Data Index: 8613229 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.3475. Min Act: -0.1700
Data Index: 7664366 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.3475. Min Act: -0.1700
Data Index: 6268459 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.3475. Min Act: -0.1700
Data Index: 5288473 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.2850. Min Act: -0.1700
Data Index: 8306943 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.2850. Min Act: -0.1700
Data Index: 6002196 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.2850. Min Act: -0.1700
Data Index: 1368971 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2850. Min Range: -10.2850
Max Act: 9.2850. Min Act: -0.1700
Data Index: 6483690 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19