Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2694 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.6921. Min Act: -0.1700
Data Index: 2870646 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.6921. Min Act: -0.1700
Data Index: 4660775 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.5671. Min Act: -0.1700
Data Index: 745354 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.5358. Min Act: -0.1700
Data Index: 5020839 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.5358. Min Act: -0.1700
Data Index: 8761575 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.5671. Min Act: -0.1700
Data Index: 4868294 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.5358. Min Act: -0.1700
Data Index: 7226812 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.5046. Min Act: -0.1700
Data Index: 549958 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.5046. Min Act: -0.1700
Data Index: 5549270 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4733. Min Act: -0.1700
Data Index: 5043161 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4421. Min Act: -0.1700
Data Index: 8791712 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4421. Min Act: -0.1700
Data Index: 8137412 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4421. Min Act: -0.1700
Data Index: 4484084 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4108. Min Act: -0.1700
Data Index: 5911927 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4421. Min Act: -0.1700
Data Index: 5130324 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4421. Min Act: -0.1700
Data Index: 4880206 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4421. Min Act: -0.1700
Data Index: 6041080 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4421. Min Act: -0.1700
Data Index: 6493403 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4108. Min Act: -0.1700
Data Index: 1841060 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6921. Min Range: -6.6921
Max Act: 6.4108. Min Act: -0.1700
Data Index: 2991100 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19