Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1194 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.9790. Min Act: -0.1700
Data Index: 5692179 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.9110. Min Act: -0.1697
Data Index: 754162 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.8255. Min Act: -0.1700
Data Index: 6801099 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.8083. Min Act: -0.1700
Data Index: 754163 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.7394. Min Act: -0.1694
Data Index: 5063189 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.7221. Min Act: -0.1698
Data Index: 2960530 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.7047. Min Act: -0.1700
Data Index: 5186092 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6874. Min Act: -0.1698
Data Index: 395881 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6874. Min Act: -0.1698
Data Index: 2560158 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.7047. Min Act: -0.1697
Data Index: 27877 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6874. Min Act: -0.1699
Data Index: 102664 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6874. Min Act: -0.1672
Data Index: 4630387 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6526. Min Act: -0.1700
Data Index: 5375775 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6352. Min Act: -0.1692
Data Index: 7585654 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6526. Min Act: -0.1700
Data Index: 2323217 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6352. Min Act: -0.1698
Data Index: 3630654 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6352. Min Act: -0.1700
Data Index: 8024864 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6178. Min Act: -0.1700
Data Index: 4328007 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6526. Min Act: -0.1700
Data Index: 6184586 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9790. Min Range: -1.9790
Max Act: 1.6003. Min Act: -0.1697
Data Index: 5310229 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19