Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4228 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2159. Min Range: -7.2159
Max Act: 7.2159. Min Act: -0.1700
Data Index: 3887097 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.9971. Min Act: -0.1700
Data Index: 1647872 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.9971. Min Act: -0.1700
Data Index: 5588018 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.9971. Min Act: -0.1700
Data Index: 7116454 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.9034. Min Act: -0.1700
Data Index: 5886222 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.8721. Min Act: -0.1700
Data Index: 3845 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.8409. Min Act: -0.1700
Data Index: 5961736 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.8096. Min Act: -0.1700
Data Index: 7733486 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.8409. Min Act: -0.1700
Data Index: 8694045 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.8096. Min Act: -0.1700
Data Index: 5274856 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.7784. Min Act: -0.1700
Data Index: 6284232 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.7159. Min Act: -0.1700
Data Index: 7209067 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.6221. Min Act: -0.1700
Data Index: 1077576 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.5909. Min Act: -0.1700
Data Index: 8406540 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.5909. Min Act: -0.1700
Data Index: 8226590 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.5284. Min Act: -0.1700
Data Index: 146066 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.5284. Min Act: -0.1700
Data Index: 562267 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.4971. Min Act: -0.1700
Data Index: 3868991 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.4971. Min Act: -0.1700
Data Index: 3125577 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2159. Min Range: -7.2159
Max Act: 6.4971. Min Act: -0.1700
Data Index: 663245 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19