Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5350 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3931. Min Act: -0.1700
Data Index: 5473635 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3303. Min Act: -0.1700
Data Index: 3250087 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3303. Min Act: -0.1700
Data Index: 1756796 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2675. Min Act: -0.1700
Data Index: 4690428 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2675. Min Act: -0.1700
Data Index: 647676 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2361. Min Act: -0.1700
Data Index: 5295056 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2675. Min Act: -0.1700
Data Index: 8054697 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2204. Min Act: -0.1700
Data Index: 5284009 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2204. Min Act: -0.1700
Data Index: 8160881 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2361. Min Act: -0.1700
Data Index: 7623848 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2047. Min Act: -0.1700
Data Index: 1070619 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2047. Min Act: -0.1700
Data Index: 8399913 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.1732. Min Act: -0.1700
Data Index: 1177109 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.1575. Min Act: -0.1700
Data Index: 961840 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.1575. Min Act: -0.1700
Data Index: 2001273 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.1417. Min Act: -0.1700
Data Index: 6418570 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.1260. Min Act: -0.1700
Data Index: 7591020 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.1260. Min Act: -0.1700
Data Index: 6723309 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.0945. Min Act: -0.1700
Data Index: 4636945 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.1102. Min Act: -0.1700
Data Index: 8274839 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19