Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0795. Min Range: -8.0795
Max Act: 8.0795. Min Act: -0.1700
Data Index: 654792 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.4545. Min Act: -0.1700
Data Index: 1454783 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.3607. Min Act: -0.1700
Data Index: 5419552 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.3295. Min Act: -0.1700
Data Index: 7661428 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.2357. Min Act: -0.1700
Data Index: 1960016 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.2357. Min Act: -0.1700
Data Index: 6291329 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.2670. Min Act: -0.1700
Data Index: 4742416 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.1732. Min Act: -0.1700
Data Index: 4232759 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.1420. Min Act: -0.1700
Data Index: 4632614 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.1732. Min Act: -0.1700
Data Index: 564828 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.0482. Min Act: -0.1700
Data Index: 677442 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.0482. Min Act: -0.1700
Data Index: 8457063 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.0170. Min Act: -0.1700
Data Index: 4087078 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.0170. Min Act: -0.1700
Data Index: 8684460 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0795. Min Range: -8.0795
Max Act: 6.9857. Min Act: -0.1700
Data Index: 2618433 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0795. Min Range: -8.0795
Max Act: 7.0170. Min Act: -0.1700
Data Index: 4287478 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0795. Min Range: -8.0795
Max Act: 6.9545. Min Act: -0.1700
Data Index: 1020428 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0795. Min Range: -8.0795
Max Act: 6.9232. Min Act: -0.1700
Data Index: 4197492 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0795. Min Range: -8.0795
Max Act: 6.8607. Min Act: -0.1700
Data Index: 1591858 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0795. Min Range: -8.0795
Max Act: 6.8295. Min Act: -0.1700
Data Index: 4284855 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19