Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.3512. Min Act: -0.1700
Data Index: 4298853 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.2887. Min Act: -0.1700
Data Index: 4298839 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.2575. Min Act: -0.1700
Data Index: 7356267 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.2575. Min Act: -0.1700
Data Index: 3575067 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.1012. Min Act: -0.1700
Data Index: 6975144 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.1637. Min Act: -0.1700
Data Index: 5509096 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.1012. Min Act: -0.1700
Data Index: 176566 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.1324. Min Act: -0.1700
Data Index: 5509109 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.1012. Min Act: -0.1700
Data Index: 3871569 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.0699. Min Act: -0.1700
Data Index: 5611410 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.0699. Min Act: -0.1700
Data Index: 6105673 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.0387. Min Act: -0.1700
Data Index: 7494718 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.0387. Min Act: -0.1700
Data Index: 8689537 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.0387. Min Act: -0.1700
Data Index: 8271576 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.0074. Min Act: -0.1700
Data Index: 2983492 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3512. Min Range: -4.3512
Max Act: 4.0074. Min Act: -0.1700
Data Index: 2644307 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3512. Min Range: -4.3512
Max Act: 3.9449. Min Act: -0.1700
Data Index: 6422314 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3512. Min Range: -4.3512
Max Act: 3.9762. Min Act: -0.1700
Data Index: 8493321 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3512. Min Range: -4.3512
Max Act: 3.9762. Min Act: -0.1700
Data Index: 2392828 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3512. Min Range: -4.3512
Max Act: 3.9449. Min Act: -0.1700
Data Index: 3800588 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19