Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1805 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.9548. Min Act: -0.1700
Data Index: 173861 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.7048. Min Act: -0.1700
Data Index: 3463333 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.5798. Min Act: -0.1700
Data Index: 5575196 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.4236. Min Act: -0.1700
Data Index: 4655120 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.4236. Min Act: -0.1700
Data Index: 5870909 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.4548. Min Act: -0.1700
Data Index: 7544852 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.3923. Min Act: -0.1700
Data Index: 1506100 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.3298. Min Act: -0.1700
Data Index: 8197866 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.2986. Min Act: -0.1700
Data Index: 2306509 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.2673. Min Act: -0.1700
Data Index: 5903409 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.2048. Min Act: -0.1700
Data Index: 517642 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.2673. Min Act: -0.1700
Data Index: 8244653 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.2048. Min Act: -0.1700
Data Index: 604012 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.2048. Min Act: -0.1700
Data Index: 2810766 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.1736. Min Act: -0.1700
Data Index: 7544850 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.1423. Min Act: -0.1700
Data Index: 4716335 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.1423. Min Act: -0.1700
Data Index: 2565079 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.1423. Min Act: -0.1700
Data Index: 6750170 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.1111. Min Act: -0.1700
Data Index: 5589763 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9548. Min Range: -5.9548
Max Act: 5.0486. Min Act: -0.1700
Data Index: 2876841 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19