Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3328. Min Range: -7.3328
Max Act: 7.3328. Min Act: -0.1700
Data Index: 2834457 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3328. Min Range: -7.3328
Max Act: 7.2078. Min Act: -0.1700
Data Index: 7812584 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3328. Min Range: -7.3328
Max Act: 7.0515. Min Act: -0.1700
Data Index: 8104000 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.9890. Min Act: -0.1700
Data Index: 3234505 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.9265. Min Act: -0.1700
Data Index: 7590097 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.9578. Min Act: -0.1700
Data Index: 6629624 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.9578. Min Act: -0.1700
Data Index: 5939614 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.9265. Min Act: -0.1700
Data Index: 396844 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.8953. Min Act: -0.1700
Data Index: 8383746 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.8640. Min Act: -0.1700
Data Index: 5727615 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.8640. Min Act: -0.1700
Data Index: 3294271 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.8640. Min Act: -0.1700
Data Index: 4151454 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.8328. Min Act: -0.1700
Data Index: 3497506 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.8328. Min Act: -0.1700
Data Index: 7345849 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.8328. Min Act: -0.1700
Data Index: 4510572 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.8015. Min Act: -0.1700
Data Index: 8200937 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.7703. Min Act: -0.1700
Data Index: 4848332 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.7390. Min Act: -0.1700
Data Index: 7809766 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.7390. Min Act: -0.1700
Data Index: 184454 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3328. Min Range: -7.3328
Max Act: 6.7390. Min Act: -0.1700
Data Index: 4526975 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19