Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4073 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8094. Min Range: -9.8094
Max Act: 9.8094. Min Act: -0.1700
Data Index: 5900848 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8094. Min Range: -9.8094
Max Act: 9.8094. Min Act: -0.1700
Data Index: 512711 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8094. Min Range: -9.8094
Max Act: 9.3094. Min Act: -0.1700
Data Index: 2212395 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8094. Min Range: -9.8094
Max Act: 9.1219. Min Act: -0.1700
Data Index: 7300894 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8094. Min Range: -9.8094
Max Act: 9.0594. Min Act: -0.1700
Data Index: 1644647 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.9969. Min Act: -0.1700
Data Index: 7369894 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.9344. Min Act: -0.1700
Data Index: 1817360 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.7469. Min Act: -0.1700
Data Index: 6401261 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.7469. Min Act: -0.1700
Data Index: 5088092 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.7469. Min Act: -0.1700
Data Index: 4792860 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.6844. Min Act: -0.1700
Data Index: 1282277 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.7469. Min Act: -0.1700
Data Index: 2086016 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.6844. Min Act: -0.1700
Data Index: 132113 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.6844. Min Act: -0.1700
Data Index: 3119457 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.6844. Min Act: -0.1700
Data Index: 2296501 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.6844. Min Act: -0.1700
Data Index: 2704710 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.6844. Min Act: -0.1700
Data Index: 541342 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.6844. Min Act: -0.1700
Data Index: 3750863 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.5594. Min Act: -0.1700
Data Index: 1339680 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8094. Min Range: -9.8094
Max Act: 8.6219. Min Act: -0.1700
Data Index: 1374004 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19