Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.6800. Min Act: -0.1700
Data Index: 981875 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.6175. Min Act: -0.1700
Data Index: 6025601 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.6175. Min Act: -0.1700
Data Index: 8060245 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.6018. Min Act: -0.1700
Data Index: 7084283 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.5862. Min Act: -0.1700
Data Index: 2374222 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.5548. Min Act: -0.1700
Data Index: 7444299 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.5392. Min Act: -0.1700
Data Index: 2186690 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.5392. Min Act: -0.1700
Data Index: 4290697 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.5392. Min Act: -0.1700
Data Index: 6832690 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.5079. Min Act: -0.1700
Data Index: 7557257 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.5235. Min Act: -0.1700
Data Index: 8545033 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.4922. Min Act: -0.1700
Data Index: 8719785 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.4922. Min Act: -0.1700
Data Index: 8147492 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.4452. Min Act: -0.1700
Data Index: 2223354 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.4609. Min Act: -0.1700
Data Index: 3081980 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.4609. Min Act: -0.1700
Data Index: 7450733 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.4609. Min Act: -0.1700
Data Index: 4794689 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.4452. Min Act: -0.1700
Data Index: 1428598 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.4452. Min Act: -0.1700
Data Index: 5671548 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6800. Min Range: -3.6800
Max Act: 3.4452. Min Act: -0.1700
Data Index: 7164336 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19