Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2262 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.6234. Min Act: -0.1700
Data Index: 1601746 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.4359. Min Act: -0.1700
Data Index: 8755728 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.4046. Min Act: -0.1700
Data Index: 3878448 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.3109. Min Act: -0.1700
Data Index: 6099247 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.2484. Min Act: -0.1700
Data Index: 1211128 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.2484. Min Act: -0.1700
Data Index: 5497616 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.2484. Min Act: -0.1700
Data Index: 4473897 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.2171. Min Act: -0.1700
Data Index: 526197 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.2171. Min Act: -0.1700
Data Index: 8320044 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.1859. Min Act: -0.1700
Data Index: 3835578 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.1859. Min Act: -0.1700
Data Index: 7660695 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.1859. Min Act: -0.1700
Data Index: 7530614 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.1546. Min Act: -0.1700
Data Index: 7042533 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.1234. Min Act: -0.1700
Data Index: 4296295 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.1234. Min Act: -0.1700
Data Index: 6310139 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.0921. Min Act: -0.1700
Data Index: 604639 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.0921. Min Act: -0.1700
Data Index: 1656357 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.0609. Min Act: -0.1700
Data Index: 3617035 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.0921. Min Act: -0.1700
Data Index: 3446269 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6234. Min Range: -7.6234
Max Act: 7.0921. Min Act: -0.1700
Data Index: 5030189 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19