Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.2596. Min Act: -0.1700
Data Index: 5339341 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.1971. Min Act: -0.1700
Data Index: 1460453 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.1971. Min Act: -0.1700
Data Index: 1936119 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.1659. Min Act: -0.1700
Data Index: 7022545 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0408. Min Act: -0.1700
Data Index: 8198022 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0721. Min Act: -0.1700
Data Index: 8811075 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0721. Min Act: -0.1700
Data Index: 4889271 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0408. Min Act: -0.1700
Data Index: 605256 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0408. Min Act: -0.1700
Data Index: 7069487 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0408. Min Act: -0.1700
Data Index: 5339350 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0096. Min Act: -0.1700
Data Index: 6907216 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0096. Min Act: -0.1700
Data Index: 806790 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0096. Min Act: -0.1700
Data Index: 6143709 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0096. Min Act: -0.1700
Data Index: 7362803 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0408. Min Act: -0.1700
Data Index: 6102786 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2596. Min Range: -4.2596
Max Act: 4.0408. Min Act: -0.1700
Data Index: 5750253 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2596. Min Range: -4.2596
Max Act: 3.9783. Min Act: -0.1700
Data Index: 6438076 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2596. Min Range: -4.2596
Max Act: 3.9783. Min Act: -0.1700
Data Index: 2830900 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2596. Min Range: -4.2596
Max Act: 3.9783. Min Act: -0.1700
Data Index: 7632037 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2596. Min Range: -4.2596
Max Act: 3.9783. Min Act: -0.1700
Data Index: 1172928 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19