Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.8923. Min Act: -0.1698
Data Index: 4973611 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.6736. Min Act: -0.1700
Data Index: 5580130 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.6423. Min Act: -0.1700
Data Index: 4277643 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5798. Min Act: -0.1700
Data Index: 7416618 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.6111. Min Act: -0.1700
Data Index: 7605795 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5798. Min Act: -0.1700
Data Index: 2542171 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5486. Min Act: -0.1700
Data Index: 4533584 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5486. Min Act: -0.1700
Data Index: 2989654 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5486. Min Act: -0.1700
Data Index: 7642645 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5486. Min Act: -0.1700
Data Index: 334897 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5173. Min Act: -0.1700
Data Index: 6270689 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5486. Min Act: -0.1700
Data Index: 8497612 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5173. Min Act: -0.1700
Data Index: 5207465 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5486. Min Act: -0.1699
Data Index: 4896329 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5486. Min Act: -0.1700
Data Index: 3265990 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5173. Min Act: -0.1700
Data Index: 5260273 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5173. Min Act: -0.1700
Data Index: 5297775 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5173. Min Act: -0.1700
Data Index: 1695739 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.4861. Min Act: -0.1700
Data Index: 4438932 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8923. Min Range: -4.8923
Max Act: 4.5173. Min Act: -0.1700
Data Index: 5684866 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19