Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.0787. Min Range: -6.0787
Max Act: 6.0787. Min Act: -0.1700
Data Index: 2553109 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0787. Min Range: -6.0787
Max Act: 6.0787. Min Act: -0.1700
Data Index: 2575250 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0787. Min Range: -6.0787
Max Act: 6.0162. Min Act: -0.1700
Data Index: 6957202 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0787. Min Range: -6.0787
Max Act: 6.0475. Min Act: -0.1700
Data Index: 5206261 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.9850. Min Act: -0.1700
Data Index: 1745079 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.9537. Min Act: -0.1700
Data Index: 530616 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8600. Min Act: -0.1700
Data Index: 3621613 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8600. Min Act: -0.1700
Data Index: 3712994 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8912. Min Act: -0.1700
Data Index: 3540795 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8600. Min Act: -0.1700
Data Index: 4681312 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8600. Min Act: -0.1700
Data Index: 4210318 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8287. Min Act: -0.1700
Data Index: 784033 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8287. Min Act: -0.1700
Data Index: 7664834 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.8287. Min Act: -0.1700
Data Index: 7159850 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.7662. Min Act: -0.1700
Data Index: 6694036 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.7975. Min Act: -0.1700
Data Index: 6392020 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.7350. Min Act: -0.1699
Data Index: 7423813 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.7350. Min Act: -0.1700
Data Index: 716101 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.7350. Min Act: -0.1700
Data Index: 4006616 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0787. Min Range: -6.0787
Max Act: 5.7662. Min Act: -0.1700
Data Index: 49371 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19