Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.2954. Min Act: -0.1700
Data Index: 54928 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.1797. Min Act: -0.1700
Data Index: 7524357 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.1963. Min Act: -0.1700
Data Index: 2751848 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.1130. Min Act: -0.1700
Data Index: 2711988 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.1297. Min Act: -0.1700
Data Index: 5898796 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.1297. Min Act: -0.1700
Data Index: 2084221 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.1297. Min Act: -0.1700
Data Index: 3246144 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.1464. Min Act: -0.1700
Data Index: 1313761 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.1130. Min Act: -0.1700
Data Index: 1239481 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.0962. Min Act: -0.1700
Data Index: 2786637 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.1130. Min Act: -0.1700
Data Index: 2038861 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.1130. Min Act: -0.1700
Data Index: 4140877 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.0795. Min Act: -0.1700
Data Index: 3855671 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.0795. Min Act: -0.1700
Data Index: 803636 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.0627. Min Act: -0.1700
Data Index: 6760537 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.0627. Min Act: -0.1700
Data Index: 6027411 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.0459. Min Act: -0.1700
Data Index: 6645857 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.0627. Min Act: -0.1700
Data Index: 3644644 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.0627. Min Act: -0.1700
Data Index: 2777746 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2954. Min Range: -2.2954
Max Act: 2.0627. Min Act: -0.1700
Data Index: 5780891 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19