Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.5263. Min Act: -0.1700
Data Index: 1043253 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.4326. Min Act: -0.1700
Data Index: 5670047 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.4013. Min Act: -0.1700
Data Index: 1316019 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.3701. Min Act: -0.1700
Data Index: 6049603 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.4013. Min Act: -0.1700
Data Index: 6156516 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.2763. Min Act: -0.1700
Data Index: 3172089 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.2763. Min Act: -0.1700
Data Index: 6573825 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.2451. Min Act: -0.1700
Data Index: 122589 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.2138. Min Act: -0.1700
Data Index: 7202143 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.2451. Min Act: -0.1700
Data Index: 6421071 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.2138. Min Act: -0.1700
Data Index: 4347237 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.1826. Min Act: -0.1700
Data Index: 480592 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.1826. Min Act: -0.1700
Data Index: 1363529 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.1513. Min Act: -0.1700
Data Index: 8596993 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.1513. Min Act: -0.1700
Data Index: 3897703 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.1201. Min Act: -0.1700
Data Index: 8216181 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.0888. Min Act: -0.1700
Data Index: 360968 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.1201. Min Act: -0.1700
Data Index: 900682 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.1201. Min Act: -0.1700
Data Index: 7922771 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5263. Min Range: -5.5263
Max Act: 5.1201. Min Act: -0.1700
Data Index: 4705858 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19