Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1729 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4544. Min Range: -7.4544
Max Act: 7.4544. Min Act: -0.1700
Data Index: 3270841 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4544. Min Range: -7.4544
Max Act: 7.4544. Min Act: -0.1700
Data Index: 5795518 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4544. Min Range: -7.4544
Max Act: 7.1107. Min Act: -0.1700
Data Index: 61173 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4544. Min Range: -7.4544
Max Act: 7.1419. Min Act: -0.1700
Data Index: 2723676 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4544. Min Range: -7.4544
Max Act: 7.0169. Min Act: -0.1700
Data Index: 7553192 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4544. Min Range: -7.4544
Max Act: 7.0169. Min Act: -0.1700
Data Index: 2833779 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4544. Min Range: -7.4544
Max Act: 7.0169. Min Act: -0.1700
Data Index: 7404102 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.9544. Min Act: -0.1700
Data Index: 4299167 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.9544. Min Act: -0.1700
Data Index: 1761322 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4544. Min Range: -7.4544
Max Act: 7.0169. Min Act: -0.1700
Data Index: 3737519 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.9232. Min Act: -0.1700
Data Index: 8450397 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.9544. Min Act: -0.1700
Data Index: 5858800 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.9232. Min Act: -0.1700
Data Index: 7369875 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.9232. Min Act: -0.1700
Data Index: 5282481 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.9232. Min Act: -0.1700
Data Index: 3004243 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.9232. Min Act: -0.1700
Data Index: 7054529 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.9232. Min Act: -0.1700
Data Index: 4170072 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.8919. Min Act: -0.1700
Data Index: 6652916 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.8919. Min Act: -0.1700
Data Index: 1997945 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4544. Min Range: -7.4544
Max Act: 6.8919. Min Act: -0.1700
Data Index: 2825081 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19