Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1649 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.7468. Min Act: -0.1700
Data Index: 473997 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.5281. Min Act: -0.1700
Data Index: 3249559 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.4656. Min Act: -0.1700
Data Index: 3819140 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.4343. Min Act: -0.1700
Data Index: 2388284 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.4656. Min Act: -0.1700
Data Index: 8767943 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.4031. Min Act: -0.1700
Data Index: 4719622 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.3718. Min Act: -0.1700
Data Index: 5741679 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.3406. Min Act: -0.1700
Data Index: 6260377 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.3406. Min Act: -0.1700
Data Index: 188874 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.3406. Min Act: -0.1700
Data Index: 6284035 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.3093. Min Act: -0.1700
Data Index: 2971310 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.3093. Min Act: -0.1700
Data Index: 3798862 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.2468. Min Act: -0.1700
Data Index: 2204132 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.2468. Min Act: -0.1700
Data Index: 8794401 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.2156. Min Act: -0.1700
Data Index: 1504971 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.2156. Min Act: -0.1700
Data Index: 2801003 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.2156. Min Act: -0.1700
Data Index: 6845141 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.2156. Min Act: -0.1700
Data Index: 225302 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.2468. Min Act: -0.1700
Data Index: 2117299 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7468. Min Range: -6.7468
Max Act: 6.1843. Min Act: -0.1700
Data Index: 6133576 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19