Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 920 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.7065. Min Act: -0.1700
Data Index: 1614876 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.5190. Min Act: -0.1700
Data Index: 6625278 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.3628. Min Act: -0.1700
Data Index: 8212319 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.3315. Min Act: -0.1700
Data Index: 5520108 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.2690. Min Act: -0.1700
Data Index: 8663551 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.2378. Min Act: -0.1700
Data Index: 7633661 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.2378. Min Act: -0.1700
Data Index: 3674633 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.2378. Min Act: -0.1700
Data Index: 3255255 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.2065. Min Act: -0.1700
Data Index: 6728876 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.2065. Min Act: -0.1700
Data Index: 2952931 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.1440. Min Act: -0.1700
Data Index: 5013723 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.1440. Min Act: -0.1700
Data Index: 1904457 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.1128. Min Act: -0.1700
Data Index: 3468337 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.0815. Min Act: -0.1700
Data Index: 7697801 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.0815. Min Act: -0.1700
Data Index: 270727 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.0503. Min Act: -0.1700
Data Index: 6766886 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.0190. Min Act: -0.1700
Data Index: 4121541 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.0190. Min Act: -0.1700
Data Index: 5649766 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.0190. Min Act: -0.1700
Data Index: 3449473 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7065. Min Range: -6.7065
Max Act: 6.0190. Min Act: -0.1700
Data Index: 6176505 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19