Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.4132. Min Act: -0.1700
Data Index: 7900942 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.3819. Min Act: -0.1700
Data Index: 70272 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.2882. Min Act: -0.1700
Data Index: 4081079 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.2882. Min Act: -0.1700
Data Index: 7504438 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.1632. Min Act: -0.1700
Data Index: 8811943 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.1319. Min Act: -0.1700
Data Index: 5322168 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.1007. Min Act: -0.1700
Data Index: 5711156 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.0694. Min Act: -0.1700
Data Index: 48232 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.0382. Min Act: -0.1700
Data Index: 7370662 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.0694. Min Act: -0.1700
Data Index: 2689157 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.0382. Min Act: -0.1700
Data Index: 3134075 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.0069. Min Act: -0.1700
Data Index: 7651256 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.0069. Min Act: -0.1700
Data Index: 4748148 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.0069. Min Act: -0.1700
Data Index: 3627924 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.0069. Min Act: -0.1700
Data Index: 6062851 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4132. Min Range: -6.4132
Max Act: 6.0069. Min Act: -0.1700
Data Index: 5306519 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4132. Min Range: -6.4132
Max Act: 5.9757. Min Act: -0.1700
Data Index: 2802445 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4132. Min Range: -6.4132
Max Act: 5.9757. Min Act: -0.1700
Data Index: 7680927 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4132. Min Range: -6.4132
Max Act: 5.9757. Min Act: -0.1700
Data Index: 6752031 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4132. Min Range: -6.4132
Max Act: 5.9757. Min Act: -0.1700
Data Index: 4018014 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19