Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4124 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.3989. Min Act: -0.1700
Data Index: 6973040 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.3989. Min Act: -0.1700
Data Index: 35402 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.3051. Min Act: -0.1700
Data Index: 3880207 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.3051. Min Act: -0.1700
Data Index: 8608639 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.1489. Min Act: -0.1700
Data Index: 1501534 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.1489. Min Act: -0.1700
Data Index: 1780613 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.0864. Min Act: -0.1700
Data Index: 1008299 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.0864. Min Act: -0.1700
Data Index: 1073092 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.1176. Min Act: -0.1700
Data Index: 7228596 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9926. Min Act: -0.1700
Data Index: 7689169 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9926. Min Act: -0.1700
Data Index: 3595575 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9926. Min Act: -0.1700
Data Index: 2510599 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9614. Min Act: -0.1700
Data Index: 7165390 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9926. Min Act: -0.1700
Data Index: 5423931 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9614. Min Act: -0.1700
Data Index: 7072375 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9614. Min Act: -0.1700
Data Index: 4806554 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9301. Min Act: -0.1700
Data Index: 4816468 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9301. Min Act: -0.1700
Data Index: 3405725 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.8989. Min Act: -0.1700
Data Index: 2749846 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9301. Min Act: -0.1700
Data Index: 1857554 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19