Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8732. Min Range: -6.8732
Max Act: 6.8732. Min Act: -0.1700
Data Index: 1710357 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8732. Min Range: -6.8732
Max Act: 6.5920. Min Act: -0.1700
Data Index: 7638213 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8732. Min Range: -6.8732
Max Act: 6.5607. Min Act: -0.1700
Data Index: 379964 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8732. Min Range: -6.8732
Max Act: 6.4670. Min Act: -0.1700
Data Index: 3158097 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8732. Min Range: -6.8732
Max Act: 6.4670. Min Act: -0.1700
Data Index: 1989940 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8732. Min Range: -6.8732
Max Act: 6.3732. Min Act: -0.1700
Data Index: 7928299 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8732. Min Range: -6.8732
Max Act: 6.1545. Min Act: -0.1700
Data Index: 2510894 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8732. Min Range: -6.8732
Max Act: 6.0295. Min Act: -0.1700
Data Index: 2126167 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8732. Min Range: -6.8732
Max Act: 6.0295. Min Act: -0.1700
Data Index: 6300683 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.9670. Min Act: -0.1700
Data Index: 5598315 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.9670. Min Act: -0.1700
Data Index: 8821096 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.9670. Min Act: -0.1700
Data Index: 7470355 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.9670. Min Act: -0.1700
Data Index: 8116342 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.9357. Min Act: -0.1700
Data Index: 1221303 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.9045. Min Act: -0.1700
Data Index: 3467885 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.9045. Min Act: -0.1700
Data Index: 2490765 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.8732. Min Act: -0.1700
Data Index: 4766701 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.8732. Min Act: -0.1700
Data Index: 4270097 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.8420. Min Act: -0.1700
Data Index: 8578995 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8732. Min Range: -6.8732
Max Act: 5.9045. Min Act: -0.1700
Data Index: 1471827 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19