Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1247. Min Range: -6.1247
Max Act: 6.1247. Min Act: -0.1700
Data Index: 7715807 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.9372. Min Act: -0.1700
Data Index: 8044607 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.9060. Min Act: -0.1700
Data Index: 2099602 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.9060. Min Act: -0.1699
Data Index: 5798080 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.8435. Min Act: -0.1700
Data Index: 5002238 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7810. Min Act: -0.1700
Data Index: 3534524 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.8122. Min Act: -0.1700
Data Index: 7788808 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7810. Min Act: -0.1700
Data Index: 8355666 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7810. Min Act: -0.1700
Data Index: 6260234 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7497. Min Act: -0.1700
Data Index: 8722825 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7185. Min Act: -0.1700
Data Index: 3316011 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7185. Min Act: -0.1700
Data Index: 932233 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7185. Min Act: -0.1700
Data Index: 600478 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7185. Min Act: -0.1700
Data Index: 5848593 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7185. Min Act: -0.1699
Data Index: 4367762 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.7497. Min Act: -0.1700
Data Index: 4804484 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.6872. Min Act: -0.1700
Data Index: 7084543 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.6560. Min Act: -0.1700
Data Index: 960816 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.6560. Min Act: -0.1700
Data Index: 2941314 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1247. Min Range: -6.1247
Max Act: 5.6560. Min Act: -0.1700
Data Index: 3867745 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19