Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 654 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.1575. Min Act: -0.1700
Data Index: 5946634 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.1575. Min Act: -0.1700
Data Index: 8053091 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.0950. Min Act: -0.1700
Data Index: 968972 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.0950. Min Act: -0.1700
Data Index: 820492 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.0325. Min Act: -0.1700
Data Index: 4038011 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.0638. Min Act: -0.1700
Data Index: 3407586 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.0950. Min Act: -0.1700
Data Index: 174186 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.0325. Min Act: -0.1700
Data Index: 6470932 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.0325. Min Act: -0.1700
Data Index: 5541455 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.0325. Min Act: -0.1700
Data Index: 8549745 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.0325. Min Act: -0.1700
Data Index: 6966751 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1575. Min Range: -5.1575
Max Act: 4.9700. Min Act: -0.1700
Data Index: 5379743 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1575. Min Range: -5.1575
Max Act: 5.0013. Min Act: -0.1700
Data Index: 4724288 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1575. Min Range: -5.1575
Max Act: 4.9700. Min Act: -0.1700
Data Index: 6906000 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1575. Min Range: -5.1575
Max Act: 4.9700. Min Act: -0.1700
Data Index: 2038109 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1575. Min Range: -5.1575
Max Act: 4.9700. Min Act: -0.1700
Data Index: 1688256 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1575. Min Range: -5.1575
Max Act: 4.9388. Min Act: -0.1700
Data Index: 4724635 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1575. Min Range: -5.1575
Max Act: 4.9075. Min Act: -0.1700
Data Index: 437126 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1575. Min Range: -5.1575
Max Act: 4.9388. Min Act: -0.1700
Data Index: 610403 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1575. Min Range: -5.1575
Max Act: 4.9700. Min Act: -0.1700
Data Index: 3209372 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19