Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.4309. Min Act: -0.1121
Data Index: 135318 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.4045. Min Act: -0.1498
Data Index: 8602423 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.4045. Min Act: -0.1486
Data Index: 6290573 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3692. Min Act: -0.1537
Data Index: 1707964 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3604. Min Act: -0.1562
Data Index: 3133161 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3516. Min Act: -0.1572
Data Index: 1058820 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3516. Min Act: -0.1137
Data Index: 7785150 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3516. Min Act: -0.1547
Data Index: 1877097 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3516. Min Act: -0.1600
Data Index: 7750067 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3339. Min Act: -0.1634
Data Index: 4428867 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3428. Min Act: -0.1390
Data Index: 3709225 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3428. Min Act: -0.1572
Data Index: 6113399 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3428. Min Act: -0.1634
Data Index: 5163992 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3339. Min Act: -0.1371
Data Index: 2114485 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3428. Min Act: -0.1634
Data Index: 879029 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3339. Min Act: -0.1641
Data Index: 4704415 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3339. Min Act: -0.1292
Data Index: 2238656 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3251. Min Act: -0.1447
Data Index: 4646615 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3339. Min Act: -0.1594
Data Index: 6458311 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4309. Min Range: -1.4309
Max Act: 1.3251. Min Act: -0.1222
Data Index: 213093 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19