Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5366 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.3040. Min Act: -0.1700
Data Index: 8643946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.2883. Min Act: -0.1700
Data Index: 5677397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.2097. Min Act: -0.1700
Data Index: 6575490 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.2097. Min Act: -0.1700
Data Index: 604692 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1940. Min Act: -0.1700
Data Index: 6160330 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1940. Min Act: -0.1700
Data Index: 4323597 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1940. Min Act: -0.1700
Data Index: 1488183 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1783. Min Act: -0.1700
Data Index: 4666652 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1783. Min Act: -0.1700
Data Index: 3111862 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1783. Min Act: -0.1700
Data Index: 6576589 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1783. Min Act: -0.1700
Data Index: 632433 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1625. Min Act: -0.1700
Data Index: 785403 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1783. Min Act: -0.1700
Data Index: 793261 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1625. Min Act: -0.1700
Data Index: 2715930 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1625. Min Act: -0.1700
Data Index: 973912 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1625. Min Act: -0.1700
Data Index: 2065964 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1625. Min Act: -0.1700
Data Index: 3163471 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1625. Min Act: -0.1700
Data Index: 7207514 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1625. Min Act: -0.1700
Data Index: 7881173 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3040. Min Range: -3.3040
Max Act: 3.1625. Min Act: -0.1700
Data Index: 3313945 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19