Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2840. Min Range: -5.2840
Max Act: 5.2840. Min Act: -0.1700
Data Index: 7533199 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2840. Min Range: -5.2840
Max Act: 5.1903. Min Act: -0.1700
Data Index: 6960367 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2840. Min Range: -5.2840
Max Act: 5.1590. Min Act: -0.1700
Data Index: 8119767 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2840. Min Range: -5.2840
Max Act: 5.1278. Min Act: -0.1700
Data Index: 461505 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2840. Min Range: -5.2840
Max Act: 5.0028. Min Act: -0.1700
Data Index: 721532 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.9715. Min Act: -0.1700
Data Index: 4789743 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.9715. Min Act: -0.1700
Data Index: 8515461 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.9403. Min Act: -0.1700
Data Index: 1634607 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.9090. Min Act: -0.1700
Data Index: 8057620 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.8778. Min Act: -0.1700
Data Index: 1375775 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.8778. Min Act: -0.1700
Data Index: 6611947 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.9090. Min Act: -0.1700
Data Index: 4059618 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.8465. Min Act: -0.1700
Data Index: 4915218 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.8778. Min Act: -0.1700
Data Index: 2163335 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.8465. Min Act: -0.1700
Data Index: 6216184 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.8465. Min Act: -0.1700
Data Index: 8565797 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.8465. Min Act: -0.1700
Data Index: 3363109 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.8778. Min Act: -0.1700
Data Index: 8022872 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.8153. Min Act: -0.1700
Data Index: 7094387 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2840. Min Range: -5.2840
Max Act: 4.7840. Min Act: -0.1700
Data Index: 913066 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19