Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0080. Min Range: -6.0080
Max Act: 6.0080. Min Act: -0.1700
Data Index: 6008781 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.9455. Min Act: -0.1700
Data Index: 375673 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.8830. Min Act: -0.1700
Data Index: 519254 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.8517. Min Act: -0.1700
Data Index: 3422983 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.7892. Min Act: -0.1700
Data Index: 8611504 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.7892. Min Act: -0.1700
Data Index: 6639747 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.7267. Min Act: -0.1700
Data Index: 8314937 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.6330. Min Act: -0.1700
Data Index: 6414129 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.6330. Min Act: -0.1700
Data Index: 7603220 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.6642. Min Act: -0.1700
Data Index: 5558469 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.6017. Min Act: -0.1700
Data Index: 6320767 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.5705. Min Act: -0.1700
Data Index: 8730412 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.5705. Min Act: -0.1700
Data Index: 839738 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.5705. Min Act: -0.1700
Data Index: 3509971 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.6017. Min Act: -0.1700
Data Index: 2558482 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.5705. Min Act: -0.1700
Data Index: 389900 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.5705. Min Act: -0.1700
Data Index: 1382914 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.5705. Min Act: -0.1700
Data Index: 4785158 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.5392. Min Act: -0.1700
Data Index: 2174018 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0080. Min Range: -6.0080
Max Act: 5.5392. Min Act: -0.1700
Data Index: 2985919 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19