Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.9621. Min Act: -0.1700
Data Index: 2811450 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.9621. Min Act: -0.1700
Data Index: 6154913 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.9309. Min Act: -0.1700
Data Index: 5650374 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8996. Min Act: -0.1700
Data Index: 3717666 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8527. Min Act: -0.1700
Data Index: 793479 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8683. Min Act: -0.1700
Data Index: 2757182 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8527. Min Act: -0.1700
Data Index: 8480514 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8214. Min Act: -0.1700
Data Index: 4903134 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8371. Min Act: -0.1700
Data Index: 2201203 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8214. Min Act: -0.1700
Data Index: 5543419 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8058. Min Act: -0.1700
Data Index: 1243902 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7745. Min Act: -0.1700
Data Index: 2435675 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7745. Min Act: -0.1700
Data Index: 1150617 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7745. Min Act: -0.1700
Data Index: 6511419 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7589. Min Act: -0.1700
Data Index: 3088113 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7432. Min Act: -0.1700
Data Index: 7326791 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7589. Min Act: -0.1700
Data Index: 541105 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7589. Min Act: -0.1700
Data Index: 2204035 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7745. Min Act: -0.1700
Data Index: 2811451 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7589. Min Act: -0.1700
Data Index: 5573929 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19