Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.9710. Min Act: -0.1700
Data Index: 5307141 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.9397. Min Act: -0.1700
Data Index: 2104618 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8459. Min Act: -0.1700
Data Index: 2921047 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8303. Min Act: -0.1700
Data Index: 2141472 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.7990. Min Act: -0.1700
Data Index: 2988304 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.7677. Min Act: -0.1700
Data Index: 773559 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.6739. Min Act: -0.1700
Data Index: 953962 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.6426. Min Act: -0.1700
Data Index: 4237650 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.6739. Min Act: -0.1700
Data Index: 4373654 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.6269. Min Act: -0.1700
Data Index: 1384047 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.6269. Min Act: -0.1700
Data Index: 3807015 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.5800. Min Act: -0.1700
Data Index: 4756816 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.5800. Min Act: -0.1700
Data Index: 8540562 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.5800. Min Act: -0.1700
Data Index: 8515277 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.5643. Min Act: -0.1700
Data Index: 7770184 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.5643. Min Act: -0.1700
Data Index: 4511529 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.5487. Min Act: -0.1700
Data Index: 8110407 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.5643. Min Act: -0.1700
Data Index: 663882 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.5643. Min Act: -0.1700
Data Index: 3899018 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.5487. Min Act: -0.1700
Data Index: 8154108 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19