Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2233 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0679. Min Range: -5.0679
Max Act: 5.0679. Min Act: -0.1698
Data Index: 5018751 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0679. Min Range: -5.0679
Max Act: 5.0367. Min Act: -0.1602
Data Index: 1994897 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0679. Min Range: -5.0679
Max Act: 5.0054. Min Act: -0.1700
Data Index: 1011842 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.9742. Min Act: -0.1700
Data Index: 3937839 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0679. Min Range: -5.0679
Max Act: 5.0054. Min Act: -0.1696
Data Index: 4646214 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.9429. Min Act: -0.1694
Data Index: 3770672 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.9117. Min Act: -0.1688
Data Index: 856240 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.8492. Min Act: -0.1699
Data Index: 3770657 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.8492. Min Act: -0.1699
Data Index: 2858910 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.8179. Min Act: -0.1698
Data Index: 3636524 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.8179. Min Act: -0.1608
Data Index: 3770656 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.8179. Min Act: -0.1700
Data Index: 4598773 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.7242. Min Act: -0.1700
Data Index: 3228206 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.7554. Min Act: -0.1692
Data Index: 3770670 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.7554. Min Act: -0.1700
Data Index: 7710925 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.7554. Min Act: -0.1700
Data Index: 4598777 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.7554. Min Act: -0.1698
Data Index: 4598772 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.7242. Min Act: -0.1700
Data Index: 1011849 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.7242. Min Act: -0.1700
Data Index: 3770673 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0679. Min Range: -5.0679
Max Act: 4.7242. Min Act: -0.1700
Data Index: 6358361 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19