Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.3795. Min Act: -0.1700
Data Index: 5207867 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.3482. Min Act: -0.1700
Data Index: 7904743 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.3482. Min Act: -0.1700
Data Index: 5553756 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.3170. Min Act: -0.1700
Data Index: 2666444 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2857. Min Act: -0.1700
Data Index: 1673932 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.3170. Min Act: -0.1700
Data Index: 810171 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.3170. Min Act: -0.1700
Data Index: 3522248 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.3170. Min Act: -0.1700
Data Index: 6256684 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2857. Min Act: -0.1700
Data Index: 3213015 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2857. Min Act: -0.1700
Data Index: 7758051 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2857. Min Act: -0.1700
Data Index: 1281410 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2545. Min Act: -0.1700
Data Index: 2071622 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2545. Min Act: -0.1700
Data Index: 155578 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2545. Min Act: -0.1700
Data Index: 3679457 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2545. Min Act: -0.1700
Data Index: 7343531 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2545. Min Act: -0.1700
Data Index: 7777400 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2857. Min Act: -0.1700
Data Index: 5515098 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2545. Min Act: -0.1700
Data Index: 5043145 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2545. Min Act: -0.1700
Data Index: 2542747 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3795. Min Range: -4.3795
Max Act: 4.2545. Min Act: -0.1700
Data Index: 4594909 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19