Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1932 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3580. Min Range: -6.3580
Max Act: 6.3580. Min Act: -0.1700
Data Index: 2648243 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3580. Min Range: -6.3580
Max Act: 6.1393. Min Act: -0.1700
Data Index: 5840349 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3580. Min Range: -6.3580
Max Act: 6.0455. Min Act: -0.1700
Data Index: 31061 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3580. Min Range: -6.3580
Max Act: 6.0143. Min Act: -0.1700
Data Index: 3900709 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.9518. Min Act: -0.1700
Data Index: 7771163 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.9518. Min Act: -0.1700
Data Index: 6907828 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.9205. Min Act: -0.1700
Data Index: 7457795 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.8580. Min Act: -0.1700
Data Index: 2340892 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.8580. Min Act: -0.1700
Data Index: 543573 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.8580. Min Act: -0.1700
Data Index: 3337103 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.8268. Min Act: -0.1700
Data Index: 1307819 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.8268. Min Act: -0.1700
Data Index: 2410090 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.8268. Min Act: -0.1700
Data Index: 5927659 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.8268. Min Act: -0.1700
Data Index: 8770044 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.7955. Min Act: -0.1700
Data Index: 5486000 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.7643. Min Act: -0.1700
Data Index: 889724 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.7955. Min Act: -0.1700
Data Index: 5538614 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.7955. Min Act: -0.1700
Data Index: 5024262 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.7955. Min Act: -0.1700
Data Index: 8464426 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3580. Min Range: -6.3580
Max Act: 5.8268. Min Act: -0.1700
Data Index: 2929080 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19