Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1007 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5625. Min Act: -0.1700
Data Index: 6071340 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5937. Min Act: -0.1700
Data Index: 904666 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5625. Min Act: -0.1700
Data Index: 2340683 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5312. Min Act: -0.1700
Data Index: 322601 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4687. Min Act: -0.1700
Data Index: 3122058 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4687. Min Act: -0.1700
Data Index: 8070902 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4687. Min Act: -0.1700
Data Index: 6279485 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 7863380 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 4619478 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 5907845 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 3201174 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4375. Min Act: -0.1700
Data Index: 368823 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3750. Min Act: -0.1700
Data Index: 4175725 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3750. Min Act: -0.1700
Data Index: 6591945 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3437. Min Act: -0.1700
Data Index: 8306468 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3750. Min Act: -0.1700
Data Index: 862486 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3437. Min Act: -0.1700
Data Index: 1600396 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3125. Min Act: -0.1700
Data Index: 3766691 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3125. Min Act: -0.1700
Data Index: 7808600 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.2812. Min Act: -0.1700
Data Index: 4131610 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19