Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2287 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3359. Min Range: -6.3359
Max Act: 6.3359. Min Act: -0.1700
Data Index: 649451 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3359. Min Range: -6.3359
Max Act: 6.2734. Min Act: -0.1700
Data Index: 4632497 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3359. Min Range: -6.3359
Max Act: 6.2109. Min Act: -0.1700
Data Index: 904062 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3359. Min Range: -6.3359
Max Act: 6.1484. Min Act: -0.1700
Data Index: 5919837 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3359. Min Range: -6.3359
Max Act: 6.1172. Min Act: -0.1700
Data Index: 3445981 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3359. Min Range: -6.3359
Max Act: 6.1172. Min Act: -0.1700
Data Index: 5361990 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3359. Min Range: -6.3359
Max Act: 6.0234. Min Act: -0.1700
Data Index: 4295017 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3359. Min Range: -6.3359
Max Act: 6.0547. Min Act: -0.1700
Data Index: 8442888 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3359. Min Range: -6.3359
Max Act: 6.0234. Min Act: -0.1700
Data Index: 338014 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9922. Min Act: -0.1700
Data Index: 3832176 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9922. Min Act: -0.1700
Data Index: 7067220 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9922. Min Act: -0.1700
Data Index: 6146555 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9609. Min Act: -0.1700
Data Index: 4087857 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9609. Min Act: -0.1700
Data Index: 6448392 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9609. Min Act: -0.1700
Data Index: 7415649 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9609. Min Act: -0.1700
Data Index: 712814 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9609. Min Act: -0.1700
Data Index: 2859354 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9609. Min Act: -0.1700
Data Index: 1053222 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9297. Min Act: -0.1700
Data Index: 7084202 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3359. Min Range: -6.3359
Max Act: 5.9297. Min Act: -0.1700
Data Index: 1919663 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19