Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4730 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0343. Min Range: -3.0343
Max Act: 3.0343. Min Act: -0.1700
Data Index: 3091928 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.6847. Min Act: -0.1700
Data Index: 4250903 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.6205. Min Act: -0.1700
Data Index: 8577754 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.5561. Min Act: -0.1700
Data Index: 2599380 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.5238. Min Act: -0.1700
Data Index: 609910 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.5561. Min Act: -0.1700
Data Index: 5632883 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.5399. Min Act: -0.1700
Data Index: 4382207 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.5238. Min Act: -0.1700
Data Index: 6439126 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4914. Min Act: -0.1700
Data Index: 1732971 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4914. Min Act: -0.1700
Data Index: 6589204 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4752. Min Act: -0.1700
Data Index: 855674 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4427. Min Act: -0.1700
Data Index: 1675633 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4427. Min Act: -0.1700
Data Index: 1650583 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4264. Min Act: -0.1700
Data Index: 122111 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4264. Min Act: -0.1700
Data Index: 71258 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4264. Min Act: -0.1700
Data Index: 6404172 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.3938. Min Act: -0.1700
Data Index: 919992 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4264. Min Act: -0.1700
Data Index: 1979231 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4101. Min Act: -0.1700
Data Index: 6674029 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0343. Min Range: -3.0343
Max Act: 2.4101. Min Act: -0.1700
Data Index: 3375881 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19