Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1576. Min Range: -4.1576
Max Act: 4.1576. Min Act: -0.1700
Data Index: 4179750 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1576. Min Range: -4.1576
Max Act: 4.0950. Min Act: -0.1700
Data Index: 8725252 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1576. Min Range: -4.1576
Max Act: 4.0638. Min Act: -0.1700
Data Index: 8210002 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1576. Min Range: -4.1576
Max Act: 4.0325. Min Act: -0.1700
Data Index: 1292410 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1576. Min Range: -4.1576
Max Act: 4.0013. Min Act: -0.1700
Data Index: 5498158 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.9387. Min Act: -0.1700
Data Index: 2465675 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.9387. Min Act: -0.1700
Data Index: 4275786 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.8762. Min Act: -0.1700
Data Index: 4299070 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.8449. Min Act: -0.1700
Data Index: 4328925 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.8449. Min Act: -0.1700
Data Index: 2912002 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.8137. Min Act: -0.1700
Data Index: 1304214 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.7824. Min Act: -0.1700
Data Index: 4317670 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.7511. Min Act: -0.1700
Data Index: 1435169 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.7511. Min Act: -0.1700
Data Index: 4506153 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.7511. Min Act: -0.1700
Data Index: 3420335 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.7511. Min Act: -0.1700
Data Index: 1608772 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.7511. Min Act: -0.1700
Data Index: 3180373 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.7198. Min Act: -0.1700
Data Index: 2331720 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.7511. Min Act: -0.1700
Data Index: 6966127 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1576. Min Range: -4.1576
Max Act: 3.7511. Min Act: -0.1700
Data Index: 8168687 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19