Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 570 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.4777. Min Act: -0.1700
Data Index: 1694553 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.4152. Min Act: -0.1700
Data Index: 8642241 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.3527. Min Act: -0.1700
Data Index: 3796089 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.3840. Min Act: -0.1700
Data Index: 5814815 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.2590. Min Act: -0.1700
Data Index: 3751711 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.2590. Min Act: -0.1700
Data Index: 4284494 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.2590. Min Act: -0.1700
Data Index: 3044551 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.2277. Min Act: -0.1700
Data Index: 3266180 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1965. Min Act: -0.1700
Data Index: 4154782 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.2277. Min Act: -0.1700
Data Index: 3721559 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1965. Min Act: -0.1700
Data Index: 4221498 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1965. Min Act: -0.1700
Data Index: 906091 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1652. Min Act: -0.1700
Data Index: 2917574 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1652. Min Act: -0.1700
Data Index: 2181975 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1652. Min Act: -0.1700
Data Index: 4054521 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1965. Min Act: -0.1700
Data Index: 7064434 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1339. Min Act: -0.1700
Data Index: 6497209 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1339. Min Act: -0.1700
Data Index: 6288803 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1339. Min Act: -0.1700
Data Index: 5764692 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1339. Min Act: -0.1700
Data Index: 2748579 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19