Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6286 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.8059. Min Act: -0.1700
Data Index: 4802487 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.7746. Min Act: -0.1700
Data Index: 7192977 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.6809. Min Act: -0.1700
Data Index: 1282267 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.7121. Min Act: -0.1700
Data Index: 5265462 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.7121. Min Act: -0.1700
Data Index: 7444629 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.6184. Min Act: -0.1700
Data Index: 1144612 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.6184. Min Act: -0.1700
Data Index: 8792179 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.5871. Min Act: -0.1700
Data Index: 24532 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.5559. Min Act: -0.1700
Data Index: 2498161 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4621. Min Act: -0.1700
Data Index: 3440849 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4621. Min Act: -0.1700
Data Index: 2975181 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4621. Min Act: -0.1700
Data Index: 2918704 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4621. Min Act: -0.1700
Data Index: 5007834 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4309. Min Act: -0.1700
Data Index: 4933916 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4309. Min Act: -0.1700
Data Index: 1390271 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4309. Min Act: -0.1700
Data Index: 8598618 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.4309. Min Act: -0.1700
Data Index: 4846474 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.3996. Min Act: -0.1700
Data Index: 7479567 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.3996. Min Act: -0.1700
Data Index: 1836906 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8059. Min Range: -6.8059
Max Act: 6.3371. Min Act: -0.1700
Data Index: 4338276 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19