Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2501 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.6285. Min Act: -0.1700
Data Index: 3353309 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.6129. Min Act: -0.1700
Data Index: 2733222 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5972. Min Act: -0.1700
Data Index: 5246488 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5972. Min Act: -0.1700
Data Index: 7654546 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5816. Min Act: -0.1700
Data Index: 2171326 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5346. Min Act: -0.1700
Data Index: 8728293 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5346. Min Act: -0.1700
Data Index: 4933728 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5346. Min Act: -0.1700
Data Index: 5593503 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5503. Min Act: -0.1700
Data Index: 4561810 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5346. Min Act: -0.1700
Data Index: 8422158 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5190. Min Act: -0.1700
Data Index: 2919330 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5346. Min Act: -0.1700
Data Index: 7617859 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5190. Min Act: -0.1700
Data Index: 2079407 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.5190. Min Act: -0.1700
Data Index: 7560743 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.4876. Min Act: -0.1700
Data Index: 1621522 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.4876. Min Act: -0.1700
Data Index: 1627221 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.4876. Min Act: -0.1700
Data Index: 4846223 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.4876. Min Act: -0.1700
Data Index: 7936781 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.4876. Min Act: -0.1700
Data Index: 5340826 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6285. Min Range: -3.6285
Max Act: 3.4876. Min Act: -0.1700
Data Index: 1842 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19