Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4124 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.4641. Min Act: -0.1700
Data Index: 2915453 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.3391. Min Act: -0.1700
Data Index: 4436441 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.1516. Min Act: -0.1700
Data Index: 4286100 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0579. Min Act: -0.1700
Data Index: 861666 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0266. Min Act: -0.1700
Data Index: 8362234 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4641. Min Range: -6.4641
Max Act: 6.0266. Min Act: -0.1700
Data Index: 4286101 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9641. Min Act: -0.1700
Data Index: 4274880 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9954. Min Act: -0.1700
Data Index: 1141585 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9329. Min Act: -0.1700
Data Index: 1468176 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9641. Min Act: -0.1700
Data Index: 4730294 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9954. Min Act: -0.1700
Data Index: 5929042 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9329. Min Act: -0.1700
Data Index: 1043177 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9329. Min Act: -0.1700
Data Index: 8796582 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9329. Min Act: -0.1700
Data Index: 755139 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9016. Min Act: -0.1700
Data Index: 3989613 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9016. Min Act: -0.1700
Data Index: 4880250 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.9016. Min Act: -0.1700
Data Index: 8700598 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.8704. Min Act: -0.1700
Data Index: 6094782 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.8704. Min Act: -0.1700
Data Index: 6528615 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4641. Min Range: -6.4641
Max Act: 5.8704. Min Act: -0.1700
Data Index: 1282583 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19