Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2355 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.7396. Min Act: -0.1700
Data Index: 4056662 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.7083. Min Act: -0.1700
Data Index: 7050798 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.7083. Min Act: -0.1700
Data Index: 4350362 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6458. Min Act: -0.1700
Data Index: 1180466 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6771. Min Act: -0.1700
Data Index: 7801754 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6458. Min Act: -0.1700
Data Index: 4360176 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6146. Min Act: -0.1700
Data Index: 27816 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5833. Min Act: -0.1700
Data Index: 5535269 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5833. Min Act: -0.1700
Data Index: 5385765 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5833. Min Act: -0.1700
Data Index: 2714001 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.6146. Min Act: -0.1700
Data Index: 6720642 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5521. Min Act: -0.1700
Data Index: 1883355 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5208. Min Act: -0.1700
Data Index: 3932717 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5521. Min Act: -0.1700
Data Index: 894630 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5208. Min Act: -0.1700
Data Index: 92384 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.5208. Min Act: -0.1700
Data Index: 7314884 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.4896. Min Act: -0.1700
Data Index: 5006733 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.4583. Min Act: -0.1700
Data Index: 5014298 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.4896. Min Act: -0.1700
Data Index: 5502789 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7396. Min Range: -6.7396
Max Act: 6.4583. Min Act: -0.1700
Data Index: 1745786 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19