Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 669 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5575. Min Range: -6.5575
Max Act: 6.5575. Min Act: -0.1700
Data Index: 4082247 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.9950. Min Act: -0.1700
Data Index: 3582013 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.9325. Min Act: -0.1700
Data Index: 8187073 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.7762. Min Act: -0.1700
Data Index: 8332649 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.6825. Min Act: -0.1700
Data Index: 631889 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.6512. Min Act: -0.1700
Data Index: 3160346 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.6200. Min Act: -0.1700
Data Index: 5962771 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.5887. Min Act: -0.1700
Data Index: 3444961 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.5887. Min Act: -0.1700
Data Index: 1320917 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.5575. Min Act: -0.1700
Data Index: 1884614 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.5262. Min Act: -0.1700
Data Index: 6568816 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.4950. Min Act: -0.1700
Data Index: 7280853 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.4637. Min Act: -0.1700
Data Index: 5282083 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.4637. Min Act: -0.1700
Data Index: 6513189 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.4637. Min Act: -0.1700
Data Index: 4596021 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.4325. Min Act: -0.1700
Data Index: 2994350 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.4325. Min Act: -0.1700
Data Index: 2275317 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.4012. Min Act: -0.1700
Data Index: 83487 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.4012. Min Act: -0.1700
Data Index: 1448517 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5575. Min Range: -6.5575
Max Act: 5.3700. Min Act: -0.1700
Data Index: 4707510 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19