Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6235 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.9718. Min Act: -0.1700
Data Index: 784314 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.9093. Min Act: -0.1700
Data Index: 2985929 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.9093. Min Act: -0.1700
Data Index: 2441183 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.7843. Min Act: -0.1700
Data Index: 5489601 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.7218. Min Act: -0.1700
Data Index: 237833 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.7218. Min Act: -0.1700
Data Index: 7220700 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.5343. Min Act: -0.1700
Data Index: 1988640 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.4718. Min Act: -0.1700
Data Index: 5179862 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.4093. Min Act: -0.1700
Data Index: 3917053 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.3468. Min Act: -0.1700
Data Index: 648120 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.2843. Min Act: -0.1700
Data Index: 7300672 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.2843. Min Act: -0.1700
Data Index: 132684 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.2843. Min Act: -0.1700
Data Index: 1989129 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.2843. Min Act: -0.1700
Data Index: 8050956 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.2843. Min Act: -0.1700
Data Index: 2510701 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.2843. Min Act: -0.1700
Data Index: 430762 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.2843. Min Act: -0.1700
Data Index: 3423073 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.2218. Min Act: -0.1700
Data Index: 7629732 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.2218. Min Act: -0.1700
Data Index: 655844 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9718. Min Range: -9.9718
Max Act: 9.2218. Min Act: -0.1700
Data Index: 2845274 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19