Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5158 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.6374. Min Act: -0.1700
Data Index: 2339243 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.6061. Min Act: -0.1700
Data Index: 657286 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.6061. Min Act: -0.1700
Data Index: 6471190 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5748. Min Act: -0.1700
Data Index: 8469128 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5748. Min Act: -0.1700
Data Index: 864263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5748. Min Act: -0.1700
Data Index: 3837480 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5748. Min Act: -0.1700
Data Index: 8366931 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 1962422 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 3980082 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 4661989 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 4994284 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 3720691 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 5897979 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 3452781 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 962714 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 2133839 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 6896970 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 2700970 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 6958652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6374. Min Range: -3.6374
Max Act: 3.5435. Min Act: -0.1700
Data Index: 7003242 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19