Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3353 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.2524. Min Act: -0.1700
Data Index: 6983934 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.2524. Min Act: -0.1700
Data Index: 5725306 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.2462. Min Act: -0.1700
Data Index: 3014247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.2339. Min Act: -0.1700
Data Index: 8428797 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.2339. Min Act: -0.1700
Data Index: 8370431 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.2279. Min Act: -0.1700
Data Index: 7734084 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.2159. Min Act: -0.1700
Data Index: 4708639 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.2100. Min Act: -0.1700
Data Index: 3259978 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.2041. Min Act: -0.1700
Data Index: 7507678 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.2041. Min Act: -0.1698
Data Index: 665461 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.1982. Min Act: -0.1700
Data Index: 5711064 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.1924. Min Act: -0.1700
Data Index: 1145526 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.1982. Min Act: -0.1700
Data Index: 5379841 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.1982. Min Act: -0.1700
Data Index: 2567267 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.1982. Min Act: -0.1697
Data Index: 2346290 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.1924. Min Act: -0.1697
Data Index: 173107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.1924. Min Act: -0.1700
Data Index: 6517490 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.1982. Min Act: -0.1700
Data Index: 664085 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.1924. Min Act: -0.1697
Data Index: 2111585 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2524. Min Range: -0.2524
Max Act: 0.1924. Min Act: -0.1700
Data Index: 6878732 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19