Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3316. Min Range: -6.3316
Max Act: 6.3316. Min Act: -0.1700
Data Index: 2198384 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3316. Min Range: -6.3316
Max Act: 6.2066. Min Act: -0.1700
Data Index: 5784861 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3316. Min Range: -6.3316
Max Act: 6.0504. Min Act: -0.1700
Data Index: 8249762 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3316. Min Range: -6.3316
Max Act: 6.0191. Min Act: -0.1700
Data Index: 6667971 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.9566. Min Act: -0.1700
Data Index: 6587561 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.9254. Min Act: -0.1700
Data Index: 1919430 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.8941. Min Act: -0.1700
Data Index: 2115286 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.8941. Min Act: -0.1700
Data Index: 4357755 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.8629. Min Act: -0.1700
Data Index: 3352384 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.8316. Min Act: -0.1700
Data Index: 7047014 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.8629. Min Act: -0.1700
Data Index: 8184397 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.8316. Min Act: -0.1700
Data Index: 4622709 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.7691. Min Act: -0.1700
Data Index: 3159462 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.7691. Min Act: -0.1700
Data Index: 3355708 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.8004. Min Act: -0.1700
Data Index: 8475508 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.8004. Min Act: -0.1700
Data Index: 4285208 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.7691. Min Act: -0.1700
Data Index: 7412680 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.7379. Min Act: -0.1700
Data Index: 5254793 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.7379. Min Act: -0.1700
Data Index: 8150228 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3316. Min Range: -6.3316
Max Act: 5.7066. Min Act: -0.1700
Data Index: 1819478 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19