Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4135 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2515. Min Range: -6.2515
Max Act: 6.2515. Min Act: -0.1700
Data Index: 7960994 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2515. Min Range: -6.2515
Max Act: 6.0015. Min Act: -0.1700
Data Index: 5976932 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2515. Min Range: -6.2515
Max Act: 6.0015. Min Act: -0.1700
Data Index: 4576033 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.8140. Min Act: -0.1700
Data Index: 775997 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.8452. Min Act: -0.1700
Data Index: 7032891 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.8140. Min Act: -0.1700
Data Index: 7288049 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.7827. Min Act: -0.1700
Data Index: 4768104 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.6890. Min Act: -0.1700
Data Index: 5668556 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.6890. Min Act: -0.1700
Data Index: 6590131 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.6577. Min Act: -0.1700
Data Index: 8789363 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.6265. Min Act: -0.1700
Data Index: 8456540 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.6577. Min Act: -0.1700
Data Index: 7396176 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.5952. Min Act: -0.1700
Data Index: 8117494 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.5640. Min Act: -0.1700
Data Index: 5365560 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.5640. Min Act: -0.1700
Data Index: 5239809 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.5640. Min Act: -0.1700
Data Index: 6294710 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.5327. Min Act: -0.1700
Data Index: 5503322 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.5327. Min Act: -0.1700
Data Index: 2836463 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.4702. Min Act: -0.1700
Data Index: 10037 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2515. Min Range: -6.2515
Max Act: 5.4702. Min Act: -0.1700
Data Index: 3605614 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19