Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6349 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4481. Min Range: -6.4481
Max Act: 6.4481. Min Act: -0.1700
Data Index: 6044634 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4481. Min Range: -6.4481
Max Act: 6.2606. Min Act: -0.1700
Data Index: 3884732 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4481. Min Range: -6.4481
Max Act: 6.2293. Min Act: -0.1700
Data Index: 2974649 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4481. Min Range: -6.4481
Max Act: 6.1668. Min Act: -0.1700
Data Index: 3966620 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4481. Min Range: -6.4481
Max Act: 6.1356. Min Act: -0.1700
Data Index: 6980000 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4481. Min Range: -6.4481
Max Act: 6.1043. Min Act: -0.1700
Data Index: 2757217 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4481. Min Range: -6.4481
Max Act: 6.1043. Min Act: -0.1700
Data Index: 29723 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4481. Min Range: -6.4481
Max Act: 6.0731. Min Act: -0.1700
Data Index: 2193964 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.9793. Min Act: -0.1700
Data Index: 412337 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.9793. Min Act: -0.1700
Data Index: 7338084 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.9793. Min Act: -0.1700
Data Index: 1578442 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.9793. Min Act: -0.1700
Data Index: 6245266 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.9481. Min Act: -0.1700
Data Index: 4998256 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.9481. Min Act: -0.1700
Data Index: 6562016 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.9168. Min Act: -0.1700
Data Index: 224578 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.8856. Min Act: -0.1700
Data Index: 5665609 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.8856. Min Act: -0.1700
Data Index: 7067815 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.8856. Min Act: -0.1700
Data Index: 7315727 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.8856. Min Act: -0.1700
Data Index: 4557698 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4481. Min Range: -6.4481
Max Act: 5.8543. Min Act: -0.1700
Data Index: 5882743 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19