Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.4373. Min Act: -0.1700
Data Index: 3091642 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.1873. Min Act: -0.1700
Data Index: 4992340 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.1560. Min Act: -0.1700
Data Index: 3701666 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.1248. Min Act: -0.1700
Data Index: 2923358 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.1248. Min Act: -0.1700
Data Index: 1349077 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.1248. Min Act: -0.1700
Data Index: 4007440 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.0935. Min Act: -0.1700
Data Index: 7637208 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.0935. Min Act: -0.1700
Data Index: 8672598 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.0623. Min Act: -0.1700
Data Index: 3554921 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.0310. Min Act: -0.1700
Data Index: 7995759 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.0310. Min Act: -0.1700
Data Index: 7912043 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.0623. Min Act: -0.1700
Data Index: 126201 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.0310. Min Act: -0.1700
Data Index: 8124070 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.0310. Min Act: -0.1700
Data Index: 2495561 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4373. Min Range: -6.4373
Max Act: 5.9998. Min Act: -0.1700
Data Index: 605713 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.0310. Min Act: -0.1700
Data Index: 6348428 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4373. Min Range: -6.4373
Max Act: 6.0310. Min Act: -0.1700
Data Index: 5649801 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4373. Min Range: -6.4373
Max Act: 5.9685. Min Act: -0.1700
Data Index: 7474603 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4373. Min Range: -6.4373
Max Act: 5.9685. Min Act: -0.1700
Data Index: 6352304 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4373. Min Range: -6.4373
Max Act: 5.9998. Min Act: -0.1700
Data Index: 412013 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19