Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3270 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.6669. Min Act: -0.1700
Data Index: 6576454 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5732. Min Act: -0.1700
Data Index: 5007131 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5419. Min Act: -0.1700
Data Index: 4079215 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.4482. Min Act: -0.1700
Data Index: 7150523 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.4482. Min Act: -0.1700
Data Index: 3017984 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3857. Min Act: -0.1700
Data Index: 8513187 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3544. Min Act: -0.1700
Data Index: 2429590 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3857. Min Act: -0.1700
Data Index: 7738300 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.4169. Min Act: -0.1700
Data Index: 2239904 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3544. Min Act: -0.1700
Data Index: 3702882 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3232. Min Act: -0.1700
Data Index: 391851 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3232. Min Act: -0.1700
Data Index: 2189764 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3232. Min Act: -0.1700
Data Index: 5574702 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3232. Min Act: -0.1700
Data Index: 5179370 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.2607. Min Act: -0.1700
Data Index: 4469448 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.2607. Min Act: -0.1700
Data Index: 8329803 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.2607. Min Act: -0.1700
Data Index: 7845905 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.2607. Min Act: -0.1700
Data Index: 5978134 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.2294. Min Act: -0.1700
Data Index: 4055608 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.2294. Min Act: -0.1700
Data Index: 3190936 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19