Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1679 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.4437. Min Act: -0.1700
Data Index: 6084310 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.3187. Min Act: -0.1700
Data Index: 551286 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.2562. Min Act: -0.1700
Data Index: 654418 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.1625. Min Act: -0.1700
Data Index: 3865114 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.1937. Min Act: -0.1700
Data Index: 7071065 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.1937. Min Act: -0.1700
Data Index: 4856610 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.1937. Min Act: -0.1700
Data Index: 7209345 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.1000. Min Act: -0.1700
Data Index: 7004821 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.1000. Min Act: -0.1700
Data Index: 7647752 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.1000. Min Act: -0.1700
Data Index: 4989587 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.0375. Min Act: -0.1700
Data Index: 7494612 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4437. Min Range: -6.4437
Max Act: 5.9750. Min Act: -0.1700
Data Index: 1293933 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.0062. Min Act: -0.1700
Data Index: 3356196 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.0375. Min Act: -0.1700
Data Index: 8267036 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.0062. Min Act: -0.1700
Data Index: 261629 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4437. Min Range: -6.4437
Max Act: 6.0062. Min Act: -0.1700
Data Index: 6640578 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4437. Min Range: -6.4437
Max Act: 5.9437. Min Act: -0.1700
Data Index: 5325149 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4437. Min Range: -6.4437
Max Act: 5.8500. Min Act: -0.1700
Data Index: 860463 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4437. Min Range: -6.4437
Max Act: 5.8812. Min Act: -0.1700
Data Index: 2360617 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4437. Min Range: -6.4437
Max Act: 5.8812. Min Act: -0.1700
Data Index: 5284702 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19