Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.4512. Min Act: -0.1700
Data Index: 3198193 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.4512. Min Act: -0.1700
Data Index: 852540 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.3887. Min Act: -0.1700
Data Index: 3198190 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.3887. Min Act: -0.1700
Data Index: 4336924 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.3887. Min Act: -0.1700
Data Index: 4806482 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.2637. Min Act: -0.1700
Data Index: 1438153 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.1387. Min Act: -0.1700
Data Index: 1095291 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.2637. Min Act: -0.1700
Data Index: 1326162 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.1387. Min Act: -0.1700
Data Index: 5079852 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.1387. Min Act: -0.1700
Data Index: 1435514 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.1387. Min Act: -0.1700
Data Index: 6281219 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.1387. Min Act: -0.1700
Data Index: 194289 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.2012. Min Act: -0.1700
Data Index: 7335967 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.0762. Min Act: -0.1700
Data Index: 1371222 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.0762. Min Act: -0.1700
Data Index: 4831391 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.1387. Min Act: -0.1700
Data Index: 2666906 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.0762. Min Act: -0.1700
Data Index: 1802128 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.0762. Min Act: -0.1700
Data Index: 4373534 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.0762. Min Act: -0.1700
Data Index: 2594241 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4512. Min Range: -9.4512
Max Act: 9.0762. Min Act: -0.1700
Data Index: 1353839 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19