Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4990. Min Range: -5.4990
Max Act: 5.4990. Min Act: -0.1700
Data Index: 2506150 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4990. Min Range: -5.4990
Max Act: 5.2803. Min Act: -0.1700
Data Index: 4536402 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4990. Min Range: -5.4990
Max Act: 5.2490. Min Act: -0.1700
Data Index: 7851322 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4990. Min Range: -5.4990
Max Act: 5.0928. Min Act: -0.1700
Data Index: 5733577 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.9990. Min Act: -0.1700
Data Index: 7561014 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.9990. Min Act: -0.1700
Data Index: 8629265 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.9990. Min Act: -0.1700
Data Index: 4259090 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.9365. Min Act: -0.1700
Data Index: 8158474 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.9365. Min Act: -0.1700
Data Index: 1323317 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.9365. Min Act: -0.1700
Data Index: 8695358 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.9053. Min Act: -0.1700
Data Index: 7031711 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.9053. Min Act: -0.1700
Data Index: 5392308 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.9053. Min Act: -0.1700
Data Index: 7007861 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.8740. Min Act: -0.1700
Data Index: 2573743 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.8740. Min Act: -0.1700
Data Index: 6469862 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.8740. Min Act: -0.1700
Data Index: 6016432 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.8428. Min Act: -0.1700
Data Index: 5022954 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.8428. Min Act: -0.1700
Data Index: 8219872 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.8115. Min Act: -0.1700
Data Index: 5079785 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4990. Min Range: -5.4990
Max Act: 4.8115. Min Act: -0.1700
Data Index: 8167549 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19