Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.4361. Min Act: -0.1700
Data Index: 2006002 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.3423. Min Act: -0.1700
Data Index: 6975222 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.3423. Min Act: -0.1700
Data Index: 2967286 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.2798. Min Act: -0.1700
Data Index: 4316064 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.2798. Min Act: -0.1700
Data Index: 53312 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.1236. Min Act: -0.1700
Data Index: 6719258 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.0923. Min Act: -0.1700
Data Index: 2351579 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.0611. Min Act: -0.1700
Data Index: 5237816 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.0611. Min Act: -0.1700
Data Index: 2554297 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9986. Min Act: -0.1700
Data Index: 5774453 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4361. Min Range: -6.4361
Max Act: 6.0298. Min Act: -0.1700
Data Index: 7238828 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9673. Min Act: -0.1700
Data Index: 6712533 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9673. Min Act: -0.1700
Data Index: 7061944 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9986. Min Act: -0.1700
Data Index: 895113 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9048. Min Act: -0.1700
Data Index: 3113821 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.8736. Min Act: -0.1700
Data Index: 7476909 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9048. Min Act: -0.1700
Data Index: 3644817 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9048. Min Act: -0.1700
Data Index: 1742290 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.9048. Min Act: -0.1700
Data Index: 3889165 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4361. Min Range: -6.4361
Max Act: 5.8736. Min Act: -0.1700
Data Index: 6001937 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19