Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.7290. Min Act: -0.1700
Data Index: 3978202 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6665. Min Act: -0.1700
Data Index: 4852221 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6352. Min Act: -0.1700
Data Index: 7070907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6352. Min Act: -0.1700
Data Index: 2600060 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6040. Min Act: -0.1700
Data Index: 1552033 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6040. Min Act: -0.1700
Data Index: 2873812 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6040. Min Act: -0.1700
Data Index: 3978199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.6040. Min Act: -0.1700
Data Index: 7676173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 5513589 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 2843693 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 8664554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 1063347 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 7677387 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 164900 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 4638628 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 112736 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 934968 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5727. Min Act: -0.1700
Data Index: 6112349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 2103429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7290. Min Range: -4.7290
Max Act: 4.5415. Min Act: -0.1700
Data Index: 2178088 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19