Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1989. Min Range: -4.1989
Max Act: 4.1989. Min Act: -0.1700
Data Index: 8072537 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1989. Min Range: -4.1989
Max Act: 4.1051. Min Act: -0.1700
Data Index: 2319062 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1989. Min Range: -4.1989
Max Act: 4.0738. Min Act: -0.1700
Data Index: 484615 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1989. Min Range: -4.1989
Max Act: 4.0426. Min Act: -0.1700
Data Index: 7787333 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1989. Min Range: -4.1989
Max Act: 4.0426. Min Act: -0.1700
Data Index: 7059638 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9801. Min Act: -0.1700
Data Index: 4144016 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9801. Min Act: -0.1700
Data Index: 5247958 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9801. Min Act: -0.1700
Data Index: 3990914 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9801. Min Act: -0.1700
Data Index: 2319063 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9488. Min Act: -0.1700
Data Index: 2582654 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9488. Min Act: -0.1700
Data Index: 3599066 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9488. Min Act: -0.1700
Data Index: 3998175 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9488. Min Act: -0.1700
Data Index: 5725614 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9488. Min Act: -0.1700
Data Index: 3821599 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9488. Min Act: -0.1700
Data Index: 1902105 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9175. Min Act: -0.1700
Data Index: 6203852 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.8863. Min Act: -0.1700
Data Index: 3838822 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9488. Min Act: -0.1700
Data Index: 6824607 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.9175. Min Act: -0.1700
Data Index: 3125306 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1989. Min Range: -4.1989
Max Act: 3.8863. Min Act: -0.1700
Data Index: 7327552 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19