Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6231 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.4241. Min Act: -0.1700
Data Index: 256299 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.3303. Min Act: -0.1700
Data Index: 3738808 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.2678. Min Act: -0.1700
Data Index: 40258 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.2366. Min Act: -0.1700
Data Index: 3874063 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.2366. Min Act: -0.1700
Data Index: 8168039 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.2366. Min Act: -0.1700
Data Index: 2517971 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.1741. Min Act: -0.1700
Data Index: 3366292 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.1428. Min Act: -0.1700
Data Index: 6011562 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.1428. Min Act: -0.1700
Data Index: 6718614 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.1428. Min Act: -0.1700
Data Index: 7835851 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.1116. Min Act: -0.1700
Data Index: 1643643 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.1116. Min Act: -0.1700
Data Index: 3172346 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.1116. Min Act: -0.1700
Data Index: 5523301 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.1116. Min Act: -0.1700
Data Index: 1197906 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.1428. Min Act: -0.1700
Data Index: 172602 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.0803. Min Act: -0.1700
Data Index: 2099187 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.0803. Min Act: -0.1700
Data Index: 2056093 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.0803. Min Act: -0.1700
Data Index: 4155297 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.0803. Min Act: -0.1700
Data Index: 473976 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4241. Min Range: -6.4241
Max Act: 6.0803. Min Act: -0.1700
Data Index: 493757 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19