Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.6344. Min Act: -0.1700
Data Index: 631550 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5718. Min Act: -0.1700
Data Index: 849288 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5718. Min Act: -0.1700
Data Index: 3488615 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5718. Min Act: -0.1700
Data Index: 2451466 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5718. Min Act: -0.1700
Data Index: 120690 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5718. Min Act: -0.1700
Data Index: 2111719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5405. Min Act: -0.1700
Data Index: 3800275 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5091. Min Act: -0.1700
Data Index: 5144697 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5405. Min Act: -0.1700
Data Index: 8699855 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5405. Min Act: -0.1700
Data Index: 7483110 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5405. Min Act: -0.1700
Data Index: 7434482 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5405. Min Act: -0.1700
Data Index: 7276675 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5091. Min Act: -0.1700
Data Index: 1289058 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5405. Min Act: -0.1700
Data Index: 5306809 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5405. Min Act: -0.1700
Data Index: 7919477 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5091. Min Act: -0.1700
Data Index: 1926909 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.4778. Min Act: -0.1700
Data Index: 6661429 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.4778. Min Act: -0.1700
Data Index: 7916002 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5091. Min Act: -0.1700
Data Index: 4000945 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6344. Min Range: -3.6344
Max Act: 3.5405. Min Act: -0.1700
Data Index: 1677288 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19