Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2299. Min Range: -3.2299
Max Act: 3.2299. Min Act: -0.1700
Data Index: 2137074 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2299. Min Range: -3.2299
Max Act: 3.1984. Min Act: -0.1700
Data Index: 3065898 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2299. Min Range: -3.2299
Max Act: 3.1355. Min Act: -0.1700
Data Index: 2611686 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2299. Min Range: -3.2299
Max Act: 3.0882. Min Act: -0.1700
Data Index: 2706809 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2299. Min Range: -3.2299
Max Act: 3.0882. Min Act: -0.1700
Data Index: 2137075 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2299. Min Range: -3.2299
Max Act: 3.0409. Min Act: -0.1700
Data Index: 8680362 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2299. Min Range: -3.2299
Max Act: 3.0251. Min Act: -0.1700
Data Index: 1190222 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.9935. Min Act: -0.1700
Data Index: 5785937 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2299. Min Range: -3.2299
Max Act: 3.0093. Min Act: -0.1700
Data Index: 1013073 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.9777. Min Act: -0.1700
Data Index: 1104024 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.9935. Min Act: -0.1700
Data Index: 1505911 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.9777. Min Act: -0.1700
Data Index: 6920898 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.9619. Min Act: -0.1700
Data Index: 2669923 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.9460. Min Act: -0.1700
Data Index: 6446727 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.9460. Min Act: -0.1700
Data Index: 6126059 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.9143. Min Act: -0.1700
Data Index: 5298692 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.8985. Min Act: -0.1700
Data Index: 328167 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.9143. Min Act: -0.1700
Data Index: 8753553 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.8985. Min Act: -0.1700
Data Index: 3789895 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2299. Min Range: -3.2299
Max Act: 2.8985. Min Act: -0.1700
Data Index: 3131209 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19