Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5672 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.9817. Min Act: -0.1700
Data Index: 7870556 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.9342. Min Act: -0.1700
Data Index: 4312092 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.9183. Min Act: -0.1700
Data Index: 1238596 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.9025. Min Act: -0.1700
Data Index: 8656511 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.8866. Min Act: -0.1700
Data Index: 3795263 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.8866. Min Act: -0.1700
Data Index: 4228020 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.8866. Min Act: -0.1700
Data Index: 4330915 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.8549. Min Act: -0.1700
Data Index: 7223318 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.8231. Min Act: -0.1700
Data Index: 2712204 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.8231. Min Act: -0.1700
Data Index: 3331748 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.7913. Min Act: -0.1700
Data Index: 2737216 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.7913. Min Act: -0.1700
Data Index: 894562 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.7913. Min Act: -0.1700
Data Index: 2427856 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.7913. Min Act: -0.1700
Data Index: 5282117 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.8072. Min Act: -0.1700
Data Index: 435212 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.7913. Min Act: -0.1700
Data Index: 6667765 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.7594. Min Act: -0.1700
Data Index: 83942 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.7753. Min Act: -0.1700
Data Index: 3022703 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.7753. Min Act: -0.1700
Data Index: 5270261 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9817. Min Range: -2.9817
Max Act: 2.7753. Min Act: -0.1700
Data Index: 3334920 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19