Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0300. Min Range: -6.0300
Max Act: 6.0300. Min Act: -0.1700
Data Index: 3442256 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.9362. Min Act: -0.1700
Data Index: 2315803 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.9050. Min Act: -0.1700
Data Index: 2418905 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.8737. Min Act: -0.1700
Data Index: 2320309 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.9050. Min Act: -0.1700
Data Index: 3108085 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.8425. Min Act: -0.1700
Data Index: 8011444 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.8112. Min Act: -0.1700
Data Index: 8672011 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.8112. Min Act: -0.1700
Data Index: 5507203 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.8112. Min Act: -0.1700
Data Index: 5192630 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7800. Min Act: -0.1700
Data Index: 863793 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7800. Min Act: -0.1700
Data Index: 2804511 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7800. Min Act: -0.1700
Data Index: 923372 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.8112. Min Act: -0.1700
Data Index: 3920809 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7800. Min Act: -0.1700
Data Index: 4545971 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.7487. Min Act: -0.1700
Data Index: 1327828 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.6862. Min Act: -0.1700
Data Index: 6581937 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.6862. Min Act: -0.1700
Data Index: 7930829 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.6550. Min Act: -0.1700
Data Index: 5597572 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.6237. Min Act: -0.1700
Data Index: 1270081 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0300. Min Range: -6.0300
Max Act: 5.6550. Min Act: -0.1700
Data Index: 5760496 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19