Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1425 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.7961. Min Act: -0.1700
Data Index: 3758945 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.7802. Min Act: -0.1700
Data Index: 3044652 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.7642. Min Act: -0.1700
Data Index: 1075982 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.7323. Min Act: -0.1700
Data Index: 3383068 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.7163. Min Act: -0.1700
Data Index: 4006001 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.6522. Min Act: -0.1700
Data Index: 292546 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.5879. Min Act: -0.1700
Data Index: 4720444 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.6040. Min Act: -0.1700
Data Index: 365480 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.6040. Min Act: -0.1700
Data Index: 392810 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.6040. Min Act: -0.1700
Data Index: 6518591 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.6040. Min Act: -0.1700
Data Index: 628070 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.5879. Min Act: -0.1700
Data Index: 4123964 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.5879. Min Act: -0.1700
Data Index: 5314070 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.5879. Min Act: -0.1700
Data Index: 5983222 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.5557. Min Act: -0.1700
Data Index: 1442570 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.5234. Min Act: -0.1700
Data Index: 5609063 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.5557. Min Act: -0.1700
Data Index: 7772233 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.5395. Min Act: -0.1700
Data Index: 5415874 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.5395. Min Act: -0.1700
Data Index: 6153508 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7961. Min Range: -2.7961
Max Act: 2.5234. Min Act: -0.1700
Data Index: 7274461 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19