Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1927 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2171. Min Range: -5.2171
Max Act: 5.2171. Min Act: -0.1700
Data Index: 1579554 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2171. Min Range: -5.2171
Max Act: 5.1858. Min Act: -0.1700
Data Index: 8109782 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2171. Min Range: -5.2171
Max Act: 5.0921. Min Act: -0.1700
Data Index: 7926599 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2171. Min Range: -5.2171
Max Act: 5.0296. Min Act: -0.1700
Data Index: 6122632 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2171. Min Range: -5.2171
Max Act: 5.0608. Min Act: -0.1700
Data Index: 4987731 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2171. Min Range: -5.2171
Max Act: 5.0296. Min Act: -0.1700
Data Index: 333793 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.9983. Min Act: -0.1700
Data Index: 5369138 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.9983. Min Act: -0.1700
Data Index: 219092 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.9983. Min Act: -0.1700
Data Index: 1663947 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.9983. Min Act: -0.1700
Data Index: 7826465 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.9671. Min Act: -0.1700
Data Index: 2194860 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.9358. Min Act: -0.1700
Data Index: 414335 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.9358. Min Act: -0.1700
Data Index: 2273976 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.8733. Min Act: -0.1700
Data Index: 4111447 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.9046. Min Act: -0.1700
Data Index: 8826829 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.9046. Min Act: -0.1700
Data Index: 8728530 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.9046. Min Act: -0.1700
Data Index: 8605865 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.8733. Min Act: -0.1700
Data Index: 8231635 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.8733. Min Act: -0.1700
Data Index: 5309935 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2171. Min Range: -5.2171
Max Act: 4.8733. Min Act: -0.1700
Data Index: 4394103 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19