Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2168 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.9460. Min Act: -0.1700
Data Index: 8756456 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.9147. Min Act: -0.1700
Data Index: 3216198 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.9147. Min Act: -0.1700
Data Index: 4879901 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.8522. Min Act: -0.1700
Data Index: 5452886 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.8522. Min Act: -0.1700
Data Index: 7724014 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.8522. Min Act: -0.1700
Data Index: 3761105 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.8210. Min Act: -0.1700
Data Index: 8015809 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.7585. Min Act: -0.1700
Data Index: 1356083 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.7585. Min Act: -0.1700
Data Index: 7871580 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.7272. Min Act: -0.1700
Data Index: 3337930 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.6960. Min Act: -0.1700
Data Index: 4900139 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.6960. Min Act: -0.1700
Data Index: 5743704 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.6960. Min Act: -0.1700
Data Index: 5046770 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.6960. Min Act: -0.1700
Data Index: 1160942 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.7272. Min Act: -0.1700
Data Index: 2799224 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.6960. Min Act: -0.1700
Data Index: 5760060 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.6647. Min Act: -0.1700
Data Index: 7520021 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.6335. Min Act: -0.1700
Data Index: 8311454 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.5710. Min Act: -0.1700
Data Index: 6456733 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9460. Min Range: -4.9460
Max Act: 4.6022. Min Act: -0.1700
Data Index: 4771524 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19