Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2057 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.2329. Min Act: -0.1700
Data Index: 7220770 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.2017. Min Act: -0.1700
Data Index: 5346918 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1704. Min Act: -0.1700
Data Index: 4374624 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1392. Min Act: -0.1700
Data Index: 8298791 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1704. Min Act: -0.1700
Data Index: 8829920 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1079. Min Act: -0.1700
Data Index: 5190609 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1392. Min Act: -0.1700
Data Index: 5481210 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1392. Min Act: -0.1700
Data Index: 2015040 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1392. Min Act: -0.1700
Data Index: 5814282 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1079. Min Act: -0.1700
Data Index: 4638647 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.0767. Min Act: -0.1700
Data Index: 2694391 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1079. Min Act: -0.1700
Data Index: 6402577 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1079. Min Act: -0.1700
Data Index: 6087910 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1079. Min Act: -0.1700
Data Index: 7225275 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.1079. Min Act: -0.1700
Data Index: 7040374 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.0767. Min Act: -0.1700
Data Index: 3625418 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.0767. Min Act: -0.1700
Data Index: 4218106 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.0767. Min Act: -0.1700
Data Index: 5580169 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.0767. Min Act: -0.1700
Data Index: 31852 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2329. Min Range: -5.2329
Max Act: 5.0767. Min Act: -0.1700
Data Index: 6460296 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19