Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4435 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.3579. Min Act: -0.1700
Data Index: 1514751 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.2017. Min Act: -0.1700
Data Index: 2967580 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.1079. Min Act: -0.1700
Data Index: 1839062 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.0142. Min Act: -0.1700
Data Index: 5493678 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.0454. Min Act: -0.1700
Data Index: 3655921 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.0767. Min Act: -0.1700
Data Index: 3585551 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3579. Min Range: -6.3579
Max Act: 6.0142. Min Act: -0.1700
Data Index: 2153919 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9829. Min Act: -0.1700
Data Index: 3878097 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9829. Min Act: -0.1700
Data Index: 1310519 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9517. Min Act: -0.1700
Data Index: 2872545 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9517. Min Act: -0.1700
Data Index: 6873449 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9517. Min Act: -0.1700
Data Index: 3878098 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9204. Min Act: -0.1700
Data Index: 2214799 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.8892. Min Act: -0.1700
Data Index: 2659743 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9204. Min Act: -0.1700
Data Index: 3581290 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.8892. Min Act: -0.1700
Data Index: 6489155 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.8892. Min Act: -0.1700
Data Index: 5103171 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.9204. Min Act: -0.1700
Data Index: 12859 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.8579. Min Act: -0.1700
Data Index: 624578 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3579. Min Range: -6.3579
Max Act: 5.8579. Min Act: -0.1700
Data Index: 4455930 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19