Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1992. Min Range: -2.1992
Max Act: 2.1992. Min Act: -0.1700
Data Index: 8235981 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1992. Min Range: -2.1992
Max Act: 2.1159. Min Act: -0.1700
Data Index: 7583772 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1992. Min Range: -2.1992
Max Act: 2.1326. Min Act: -0.1700
Data Index: 4606046 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1992. Min Range: -2.1992
Max Act: 2.0992. Min Act: -0.1698
Data Index: 8547530 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1992. Min Range: -2.1992
Max Act: 2.0151. Min Act: -0.1700
Data Index: 3796209 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1992. Min Range: -2.1992
Max Act: 2.0067. Min Act: -0.1699
Data Index: 2486805 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1992. Min Range: -2.1992
Max Act: 2.0067. Min Act: -0.1700
Data Index: 4273046 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1992. Min Range: -2.1992
Max Act: 2.0067. Min Act: -0.1700
Data Index: 5793532 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9982. Min Act: -0.1700
Data Index: 8621352 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9813. Min Act: -0.1700
Data Index: 6231072 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9813. Min Act: -0.1700
Data Index: 8495510 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9813. Min Act: -0.1700
Data Index: 8235979 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9728. Min Act: -0.1700
Data Index: 365270 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9728. Min Act: -0.1700
Data Index: 3113902 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9559. Min Act: -0.1700
Data Index: 7008701 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9644. Min Act: -0.1700
Data Index: 6652323 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9559. Min Act: -0.1700
Data Index: 2010198 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9559. Min Act: -0.1700
Data Index: 1941860 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9644. Min Act: -0.1700
Data Index: 5527757 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1992. Min Range: -2.1992
Max Act: 1.9389. Min Act: -0.1699
Data Index: 2480884 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19