Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1721 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.4582. Min Act: -0.1700
Data Index: 3959953 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.4406. Min Act: -0.1700
Data Index: 1123649 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.4054. Min Act: -0.1700
Data Index: 7427287 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.4054. Min Act: -0.1700
Data Index: 6028126 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.3878. Min Act: -0.1700
Data Index: 6683500 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.3702. Min Act: -0.1700
Data Index: 5616470 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.3525. Min Act: -0.1700
Data Index: 6957681 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.3525. Min Act: -0.1700
Data Index: 6418993 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.3173. Min Act: -0.1700
Data Index: 4211070 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.3349. Min Act: -0.1700
Data Index: 8363474 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.3173. Min Act: -0.1700
Data Index: 1429662 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.2996. Min Act: -0.1700
Data Index: 7142940 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.2996. Min Act: -0.1700
Data Index: 1760457 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.2996. Min Act: -0.1700
Data Index: 1277542 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.2996. Min Act: -0.1700
Data Index: 5783437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.2996. Min Act: -0.1700
Data Index: 7203863 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.2820. Min Act: -0.1700
Data Index: 8467333 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.2820. Min Act: -0.1700
Data Index: 56108 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.2820. Min Act: -0.1700
Data Index: 2888795 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4582. Min Range: -1.4582
Max Act: 1.2820. Min Act: -0.1700
Data Index: 6833746 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19