Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.2825. Min Act: -0.1700
Data Index: 7739064 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.1575. Min Act: -0.1700
Data Index: 3699875 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.0950. Min Act: -0.1700
Data Index: 7666132 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.0950. Min Act: -0.1700
Data Index: 8669673 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.0637. Min Act: -0.1700
Data Index: 8237172 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.0325. Min Act: -0.1700
Data Index: 3533686 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.0325. Min Act: -0.1700
Data Index: 8090737 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.0325. Min Act: -0.1700
Data Index: 8329932 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.0012. Min Act: -0.1700
Data Index: 8329935 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.0012. Min Act: -0.1700
Data Index: 6272469 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2825. Min Range: -5.2825
Max Act: 4.9700. Min Act: -0.1700
Data Index: 3209195 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2825. Min Range: -5.2825
Max Act: 5.0012. Min Act: -0.1700
Data Index: 556651 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2825. Min Range: -5.2825
Max Act: 4.9387. Min Act: -0.1700
Data Index: 1339228 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2825. Min Range: -5.2825
Max Act: 4.9700. Min Act: -0.1700
Data Index: 8663583 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2825. Min Range: -5.2825
Max Act: 4.9387. Min Act: -0.1700
Data Index: 4456913 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2825. Min Range: -5.2825
Max Act: 4.8762. Min Act: -0.1700
Data Index: 5374697 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2825. Min Range: -5.2825
Max Act: 4.9075. Min Act: -0.1700
Data Index: 5395705 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2825. Min Range: -5.2825
Max Act: 4.9387. Min Act: -0.1700
Data Index: 7653705 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2825. Min Range: -5.2825
Max Act: 4.9075. Min Act: -0.1700
Data Index: 3286298 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2825. Min Range: -5.2825
Max Act: 4.8762. Min Act: -0.1700
Data Index: 910069 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19