Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 448 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.5060. Min Act: -0.1700
Data Index: 5345147 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.3810. Min Act: -0.1700
Data Index: 6705877 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.3498. Min Act: -0.1700
Data Index: 2190799 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.3498. Min Act: -0.1700
Data Index: 2193452 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.3498. Min Act: -0.1700
Data Index: 8463296 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.1935. Min Act: -0.1700
Data Index: 6648932 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.1935. Min Act: -0.1700
Data Index: 4765154 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.1935. Min Act: -0.1700
Data Index: 4765155 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.1935. Min Act: -0.1700
Data Index: 1422233 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.1623. Min Act: -0.1700
Data Index: 744578 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.1310. Min Act: -0.1700
Data Index: 6381183 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.0998. Min Act: -0.1700
Data Index: 909690 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.0998. Min Act: -0.1700
Data Index: 1519076 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.0685. Min Act: -0.1700
Data Index: 5367856 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.0373. Min Act: -0.1700
Data Index: 4847422 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.0060. Min Act: -0.1700
Data Index: 4238624 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.0060. Min Act: -0.1700
Data Index: 357961 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.0060. Min Act: -0.1700
Data Index: 4073087 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5060. Min Range: -7.5060
Max Act: 7.0060. Min Act: -0.1700
Data Index: 8619458 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5060. Min Range: -7.5060
Max Act: 6.9748. Min Act: -0.1700
Data Index: 2100587 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19