Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3525 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.5647. Min Act: -0.1700
Data Index: 2644557 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.4397. Min Act: -0.1700
Data Index: 3097169 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.3772. Min Act: -0.1700
Data Index: 3777391 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.2209. Min Act: -0.1700
Data Index: 706763 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.1897. Min Act: -0.1700
Data Index: 5347914 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.1897. Min Act: -0.1700
Data Index: 5885954 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.1897. Min Act: -0.1700
Data Index: 4671077 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.1272. Min Act: -0.1700
Data Index: 5975429 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.0647. Min Act: -0.1700
Data Index: 4732386 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.0022. Min Act: -0.1700
Data Index: 6733585 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5647. Min Range: -6.5647
Max Act: 6.0022. Min Act: -0.1700
Data Index: 237351 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5647. Min Range: -6.5647
Max Act: 5.9709. Min Act: -0.1700
Data Index: 8136811 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5647. Min Range: -6.5647
Max Act: 5.9709. Min Act: -0.1700
Data Index: 5510447 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5647. Min Range: -6.5647
Max Act: 5.9397. Min Act: -0.1700
Data Index: 7881692 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5647. Min Range: -6.5647
Max Act: 5.9397. Min Act: -0.1700
Data Index: 632912 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5647. Min Range: -6.5647
Max Act: 5.9084. Min Act: -0.1700
Data Index: 4166544 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5647. Min Range: -6.5647
Max Act: 5.8772. Min Act: -0.1700
Data Index: 1863340 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5647. Min Range: -6.5647
Max Act: 5.8772. Min Act: -0.1700
Data Index: 3984329 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5647. Min Range: -6.5647
Max Act: 5.8459. Min Act: -0.1700
Data Index: 1706446 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5647. Min Range: -6.5647
Max Act: 5.8459. Min Act: -0.1700
Data Index: 3508312 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19