Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.5824. Min Act: -0.1700
Data Index: 226087 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.5178. Min Act: -0.1700
Data Index: 1705446 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.5178. Min Act: -0.1700
Data Index: 848030 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.5016. Min Act: -0.1700
Data Index: 5655056 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4854. Min Act: -0.1700
Data Index: 297879 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4692. Min Act: -0.1700
Data Index: 3806244 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4367. Min Act: -0.1700
Data Index: 1705447 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4529. Min Act: -0.1700
Data Index: 8327516 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4367. Min Act: -0.1700
Data Index: 2764529 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4367. Min Act: -0.1700
Data Index: 8152545 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4529. Min Act: -0.1700
Data Index: 3257225 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4041. Min Act: -0.1700
Data Index: 4079715 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4204. Min Act: -0.1700
Data Index: 4051638 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4204. Min Act: -0.1700
Data Index: 3622471 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4041. Min Act: -0.1700
Data Index: 263822 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.3878. Min Act: -0.1700
Data Index: 3685125 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4041. Min Act: -0.1700
Data Index: 2135637 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.3878. Min Act: -0.1700
Data Index: 5847841 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4041. Min Act: -0.1700
Data Index: 5135708 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5824. Min Range: -2.5824
Max Act: 2.4041. Min Act: -0.1700
Data Index: 6670416 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19