Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1142 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.3360. Min Act: -0.1697
Data Index: 6948770 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.3032. Min Act: -0.1700
Data Index: 1397400 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.2867. Min Act: -0.1678
Data Index: 3767479 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.2372. Min Act: -0.1590
Data Index: 7927959 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.2207. Min Act: -0.1699
Data Index: 5476050 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.2041. Min Act: -0.1693
Data Index: 2488314 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.2207. Min Act: -0.1696
Data Index: 4246264 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.2041. Min Act: -0.1698
Data Index: 7387974 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1709. Min Act: -0.1667
Data Index: 5738250 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.2041. Min Act: -0.1584
Data Index: 3675967 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1875. Min Act: -0.1664
Data Index: 3915066 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1875. Min Act: -0.1700
Data Index: 3585261 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1875. Min Act: -0.1584
Data Index: 1685863 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1709. Min Act: -0.1694
Data Index: 1320031 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1542. Min Act: -0.1700
Data Index: 6885164 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1542. Min Act: -0.1672
Data Index: 3330295 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1542. Min Act: -0.1686
Data Index: 2156359 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1542. Min Act: -0.1695
Data Index: 2542221 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1542. Min Act: -0.1675
Data Index: 5503774 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3360. Min Range: -2.3360
Max Act: 2.1375. Min Act: -0.1690
Data Index: 1717539 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19