Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.9655. Min Act: -0.1700
Data Index: 4692869 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.9655. Min Act: -0.1700
Data Index: 5142080 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.9343. Min Act: -0.1700
Data Index: 8749803 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.8718. Min Act: -0.1700
Data Index: 5875373 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.8718. Min Act: -0.1699
Data Index: 1847630 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.8405. Min Act: -0.1700
Data Index: 1279058 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.8405. Min Act: -0.1700
Data Index: 1389894 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.8405. Min Act: -0.1700
Data Index: 3289387 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.8093. Min Act: -0.1700
Data Index: 5792769 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.8093. Min Act: -0.1700
Data Index: 5952292 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.8093. Min Act: -0.1700
Data Index: 2595259 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.7780. Min Act: -0.1700
Data Index: 357226 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.7468. Min Act: -0.1700
Data Index: 7500765 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.7155. Min Act: -0.1700
Data Index: 569274 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.7468. Min Act: -0.1700
Data Index: 7468526 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.7155. Min Act: -0.1700
Data Index: 3435030 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.7468. Min Act: -0.1700
Data Index: 6056273 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.6843. Min Act: -0.1700
Data Index: 7240096 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.7155. Min Act: -0.1700
Data Index: 6752062 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9655. Min Range: -4.9655
Max Act: 4.6843. Min Act: -0.1700
Data Index: 3887868 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19