Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3151 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2229. Min Range: -9.2229
Max Act: 9.2229. Min Act: -0.1700
Data Index: 2998772 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.9729. Min Act: -0.1700
Data Index: 5296815 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.9729. Min Act: -0.1700
Data Index: 5188104 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.9104. Min Act: -0.1700
Data Index: 5153019 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.9104. Min Act: -0.1700
Data Index: 7439258 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.7854. Min Act: -0.1700
Data Index: 6389733 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.7854. Min Act: -0.1700
Data Index: 8333031 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.6604. Min Act: -0.1700
Data Index: 2048744 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.6604. Min Act: -0.1700
Data Index: 4992151 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.5354. Min Act: -0.1700
Data Index: 478832 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.5354. Min Act: -0.1700
Data Index: 1853692 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.5354. Min Act: -0.1700
Data Index: 5184726 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.4729. Min Act: -0.1700
Data Index: 505283 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.5354. Min Act: -0.1700
Data Index: 7378342 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.5354. Min Act: -0.1700
Data Index: 2018879 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.5354. Min Act: -0.1700
Data Index: 69204 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.4104. Min Act: -0.1700
Data Index: 7649678 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.4104. Min Act: -0.1700
Data Index: 4107267 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.4104. Min Act: -0.1700
Data Index: 3651065 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2229. Min Range: -9.2229
Max Act: 8.3479. Min Act: -0.1700
Data Index: 3853732 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19