Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1230 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.2958. Min Act: -0.1700
Data Index: 7089630 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.2958. Min Act: -0.1700
Data Index: 6324340 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.2463. Min Act: -0.1700
Data Index: 439602 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1966. Min Act: -0.1700
Data Index: 6294630 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1966. Min Act: -0.1700
Data Index: 4548278 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1800. Min Act: -0.1700
Data Index: 439601 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1634. Min Act: -0.1700
Data Index: 1632528 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1467. Min Act: -0.1700
Data Index: 6356216 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1300. Min Act: -0.1700
Data Index: 3714141 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1133. Min Act: -0.1700
Data Index: 3336997 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1300. Min Act: -0.1700
Data Index: 4002077 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1133. Min Act: -0.1700
Data Index: 6356215 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1133. Min Act: -0.1700
Data Index: 7067402 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.1133. Min Act: -0.1700
Data Index: 5547407 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.0966. Min Act: -0.1700
Data Index: 3205565 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.0966. Min Act: -0.1700
Data Index: 1862799 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.0630. Min Act: -0.1700
Data Index: 1718626 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.0798. Min Act: -0.1700
Data Index: 4297228 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.0630. Min Act: -0.1700
Data Index: 3782646 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2958. Min Range: -2.2958
Max Act: 2.0630. Min Act: -0.1700
Data Index: 3916817 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19