Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1061 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.6564. Min Act: -0.1700
Data Index: 7161733 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.3751. Min Act: -0.1700
Data Index: 7480590 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.2814. Min Act: -0.1700
Data Index: 1280911 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.2814. Min Act: -0.1700
Data Index: 6211977 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.2501. Min Act: -0.1700
Data Index: 4045645 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.1876. Min Act: -0.1700
Data Index: 5318851 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.1251. Min Act: -0.1700
Data Index: 7584895 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.1251. Min Act: -0.1700
Data Index: 4951283 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.0939. Min Act: -0.1700
Data Index: 1574238 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.1251. Min Act: -0.1700
Data Index: 7069585 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.0939. Min Act: -0.1700
Data Index: 667263 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.0939. Min Act: -0.1700
Data Index: 4157260 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.0314. Min Act: -0.1700
Data Index: 7465641 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.0314. Min Act: -0.1700
Data Index: 1538667 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.0626. Min Act: -0.1700
Data Index: 5683669 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.0001. Min Act: -0.1700
Data Index: 4754098 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.0001. Min Act: -0.1700
Data Index: 4625893 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6564. Min Range: -6.6564
Max Act: 6.0001. Min Act: -0.1700
Data Index: 6957288 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6564. Min Range: -6.6564
Max Act: 5.9689. Min Act: -0.1700
Data Index: 6917981 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6564. Min Range: -6.6564
Max Act: 5.9376. Min Act: -0.1700
Data Index: 2557677 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19