Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4787 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1202. Min Range: -5.1202
Max Act: 5.1202. Min Act: -0.1700
Data Index: 3795747 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.9952. Min Act: -0.1700
Data Index: 7490215 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.9639. Min Act: -0.1700
Data Index: 7430488 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.8389. Min Act: -0.1700
Data Index: 693548 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.8389. Min Act: -0.1700
Data Index: 8467469 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.8389. Min Act: -0.1700
Data Index: 4715156 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.8077. Min Act: -0.1700
Data Index: 4413255 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.8077. Min Act: -0.1700
Data Index: 2376344 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.7764. Min Act: -0.1700
Data Index: 4123562 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.7764. Min Act: -0.1700
Data Index: 6398543 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.7452. Min Act: -0.1700
Data Index: 3337555 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.7139. Min Act: -0.1700
Data Index: 4802378 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.7139. Min Act: -0.1700
Data Index: 2817414 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.7139. Min Act: -0.1700
Data Index: 4397418 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.6827. Min Act: -0.1700
Data Index: 2620350 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.6827. Min Act: -0.1700
Data Index: 5980133 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.6827. Min Act: -0.1700
Data Index: 1407237 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.6827. Min Act: -0.1700
Data Index: 7220458 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.6514. Min Act: -0.1700
Data Index: 5533427 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1202. Min Range: -5.1202
Max Act: 4.6514. Min Act: -0.1700
Data Index: 4326546 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19