Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1106 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.5226. Min Act: -0.1700
Data Index: 4822659 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.4913. Min Act: -0.1700
Data Index: 8634015 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.4599. Min Act: -0.1700
Data Index: 2994215 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.4286. Min Act: -0.1700
Data Index: 5759891 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.4129. Min Act: -0.1700
Data Index: 3616257 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3972. Min Act: -0.1700
Data Index: 3209837 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3972. Min Act: -0.1700
Data Index: 7668951 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3816. Min Act: -0.1700
Data Index: 2850761 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3816. Min Act: -0.1700
Data Index: 8410435 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3972. Min Act: -0.1700
Data Index: 8192378 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3972. Min Act: -0.1700
Data Index: 6106929 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3972. Min Act: -0.1700
Data Index: 3040169 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3659. Min Act: -0.1700
Data Index: 1509568 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3659. Min Act: -0.1700
Data Index: 2336470 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3659. Min Act: -0.1700
Data Index: 3641842 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3816. Min Act: -0.1700
Data Index: 8519423 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3816. Min Act: -0.1700
Data Index: 849607 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3659. Min Act: -0.1700
Data Index: 6840658 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3659. Min Act: -0.1700
Data Index: 7693570 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5226. Min Range: -3.5226
Max Act: 3.3659. Min Act: -0.1700
Data Index: 2181711 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19