Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3202 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1859. Min Range: -7.1859
Max Act: 7.1859. Min Act: -0.1700
Data Index: 6732082 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1859. Min Range: -7.1859
Max Act: 7.1546. Min Act: -0.1700
Data Index: 3587890 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1859. Min Range: -7.1859
Max Act: 7.0921. Min Act: -0.1700
Data Index: 3148038 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1859. Min Range: -7.1859
Max Act: 7.0609. Min Act: -0.1700
Data Index: 8332899 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1859. Min Range: -7.1859
Max Act: 7.0296. Min Act: -0.1700
Data Index: 8387650 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.9984. Min Act: -0.1700
Data Index: 3383324 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.9984. Min Act: -0.1700
Data Index: 2947040 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.9984. Min Act: -0.1700
Data Index: 4507457 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.9359. Min Act: -0.1700
Data Index: 4045278 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.9359. Min Act: -0.1700
Data Index: 6147669 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.9046. Min Act: -0.1700
Data Index: 1384388 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.8734. Min Act: -0.1700
Data Index: 5232362 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.8734. Min Act: -0.1700
Data Index: 6037584 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.8421. Min Act: -0.1700
Data Index: 6656200 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.8109. Min Act: -0.1700
Data Index: 1558996 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.8734. Min Act: -0.1700
Data Index: 4348809 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.7796. Min Act: -0.1700
Data Index: 4846850 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.8109. Min Act: -0.1700
Data Index: 3118726 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.8109. Min Act: -0.1700
Data Index: 3783466 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.7796. Min Act: -0.1700
Data Index: 7171647 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19