Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1761 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3743. Min Range: -6.3743
Max Act: 6.3743. Min Act: -0.1700
Data Index: 2423862 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3743. Min Range: -6.3743
Max Act: 6.3743. Min Act: -0.1700
Data Index: 8033721 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3743. Min Range: -6.3743
Max Act: 6.2181. Min Act: -0.1700
Data Index: 789518 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3743. Min Range: -6.3743
Max Act: 6.1868. Min Act: -0.1700
Data Index: 3981677 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3743. Min Range: -6.3743
Max Act: 6.1556. Min Act: -0.1700
Data Index: 38068 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3743. Min Range: -6.3743
Max Act: 6.0931. Min Act: -0.1700
Data Index: 390829 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.9993. Min Act: -0.1700
Data Index: 3210500 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.9681. Min Act: -0.1700
Data Index: 6222035 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.9056. Min Act: -0.1700
Data Index: 1927182 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.8743. Min Act: -0.1700
Data Index: 3837690 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.9056. Min Act: -0.1700
Data Index: 3981676 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.9056. Min Act: -0.1700
Data Index: 2519326 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.9056. Min Act: -0.1700
Data Index: 8275296 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.8743. Min Act: -0.1700
Data Index: 1672309 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.8431. Min Act: -0.1700
Data Index: 5798700 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.8431. Min Act: -0.1700
Data Index: 4354659 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.8431. Min Act: -0.1700
Data Index: 7791248 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.8118. Min Act: -0.1700
Data Index: 8041136 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.8118. Min Act: -0.1700
Data Index: 1241922 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3743. Min Range: -6.3743
Max Act: 5.7806. Min Act: -0.1700
Data Index: 8601692 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19