Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.9056. Min Act: -0.1700
Data Index: 4647596 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.9056. Min Act: -0.1700
Data Index: 1048199 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.8743. Min Act: -0.1700
Data Index: 1986688 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.8431. Min Act: -0.1700
Data Index: 5360534 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.8118. Min Act: -0.1700
Data Index: 6056448 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.8118. Min Act: -0.1700
Data Index: 8612631 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7806. Min Act: -0.1700
Data Index: 1339934 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7806. Min Act: -0.1700
Data Index: 7437183 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7493. Min Act: -0.1700
Data Index: 1362090 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7493. Min Act: -0.1700
Data Index: 6420516 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7493. Min Act: -0.1700
Data Index: 6862746 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.7181. Min Act: -0.1700
Data Index: 155436 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6556. Min Act: -0.1700
Data Index: 8226482 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6868. Min Act: -0.1700
Data Index: 489676 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6868. Min Act: -0.1700
Data Index: 7825371 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6868. Min Act: -0.1700
Data Index: 7020967 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6556. Min Act: -0.1700
Data Index: 2729519 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6556. Min Act: -0.1700
Data Index: 3564073 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6556. Min Act: -0.1700
Data Index: 989048 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9056. Min Range: -4.9056
Max Act: 4.6556. Min Act: -0.1700
Data Index: 810914 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19