Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1565 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.3709. Min Act: -0.1700
Data Index: 6278465 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.1667. Min Act: -0.1700
Data Index: 6949375 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.1509. Min Act: -0.1700
Data Index: 2410406 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.1352. Min Act: -0.1700
Data Index: 6216961 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.1509. Min Act: -0.1700
Data Index: 198874 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0722. Min Act: -0.1700
Data Index: 5149462 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0722. Min Act: -0.1700
Data Index: 5741057 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0722. Min Act: -0.1700
Data Index: 1633042 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0722. Min Act: -0.1700
Data Index: 1475231 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0406. Min Act: -0.1700
Data Index: 7688147 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0406. Min Act: -0.1700
Data Index: 6558902 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0248. Min Act: -0.1700
Data Index: 3730178 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3709. Min Range: -3.3709
Max Act: 2.9932. Min Act: -0.1700
Data Index: 6939678 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0248. Min Act: -0.1700
Data Index: 4717919 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0248. Min Act: -0.1700
Data Index: 897359 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0090. Min Act: -0.1700
Data Index: 2976788 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3709. Min Range: -3.3709
Max Act: 3.0248. Min Act: -0.1700
Data Index: 7389023 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3709. Min Range: -3.3709
Max Act: 2.9774. Min Act: -0.1700
Data Index: 4979257 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3709. Min Range: -3.3709
Max Act: 2.9774. Min Act: -0.1700
Data Index: 1865793 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3709. Min Range: -3.3709
Max Act: 2.9932. Min Act: -0.1700
Data Index: 3865204 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19