Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2819 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.8363. Min Act: -0.1700
Data Index: 7177442 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.8050. Min Act: -0.1700
Data Index: 2274685 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.7425. Min Act: -0.1700
Data Index: 8474009 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.7113. Min Act: -0.1700
Data Index: 8691396 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.6488. Min Act: -0.1700
Data Index: 7493116 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.6488. Min Act: -0.1700
Data Index: 1123611 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.6488. Min Act: -0.1700
Data Index: 6098681 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.5863. Min Act: -0.1700
Data Index: 257393 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.5550. Min Act: -0.1700
Data Index: 2061391 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.5238. Min Act: -0.1700
Data Index: 149341 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.4925. Min Act: -0.1700
Data Index: 1890864 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.4925. Min Act: -0.1700
Data Index: 6061436 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.4925. Min Act: -0.1700
Data Index: 5360454 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.4925. Min Act: -0.1700
Data Index: 6805480 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.4300. Min Act: -0.1700
Data Index: 2993135 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.4613. Min Act: -0.1700
Data Index: 1640679 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.4613. Min Act: -0.1700
Data Index: 4723778 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.4925. Min Act: -0.1700
Data Index: 178161 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.4613. Min Act: -0.1700
Data Index: 1798385 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8363. Min Range: -4.8363
Max Act: 4.4613. Min Act: -0.1700
Data Index: 3215303 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19