Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1697 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.7659. Min Act: -0.1700
Data Index: 8720446 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.5159. Min Act: -0.1700
Data Index: 4803283 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.4221. Min Act: -0.1700
Data Index: 1676662 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.4534. Min Act: -0.1700
Data Index: 1193126 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.3284. Min Act: -0.1700
Data Index: 5108526 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.3596. Min Act: -0.1700
Data Index: 8321157 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.2971. Min Act: -0.1700
Data Index: 4799232 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.2346. Min Act: -0.1700
Data Index: 6695422 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.2346. Min Act: -0.1700
Data Index: 5331528 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.1721. Min Act: -0.1700
Data Index: 6213054 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.2034. Min Act: -0.1700
Data Index: 977483 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.1721. Min Act: -0.1700
Data Index: 964859 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.1721. Min Act: -0.1700
Data Index: 130040 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.1096. Min Act: -0.1700
Data Index: 5315136 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.1409. Min Act: -0.1700
Data Index: 3558169 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.1409. Min Act: -0.1700
Data Index: 2162077 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.1721. Min Act: -0.1700
Data Index: 360152 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.1409. Min Act: -0.1700
Data Index: 2317574 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.1409. Min Act: -0.1700
Data Index: 2816122 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7659. Min Range: -5.7659
Max Act: 5.1096. Min Act: -0.1700
Data Index: 3481753 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19