Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7328. Min Range: -6.7328
Max Act: 6.7328. Min Act: -0.1700
Data Index: 5094993 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7328. Min Range: -6.7328
Max Act: 6.2953. Min Act: -0.1700
Data Index: 6081228 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7328. Min Range: -6.7328
Max Act: 6.0453. Min Act: -0.1700
Data Index: 3883120 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7328. Min Range: -6.7328
Max Act: 6.0453. Min Act: -0.1700
Data Index: 4845946 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.8266. Min Act: -0.1700
Data Index: 6255951 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.7953. Min Act: -0.1700
Data Index: 6722999 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.7641. Min Act: -0.1700
Data Index: 1268996 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.7641. Min Act: -0.1700
Data Index: 8794600 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.7641. Min Act: -0.1700
Data Index: 6228129 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.7328. Min Act: -0.1700
Data Index: 8517143 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.7328. Min Act: -0.1700
Data Index: 4456077 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.7328. Min Act: -0.1700
Data Index: 4357684 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.6703. Min Act: -0.1700
Data Index: 7401812 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.7016. Min Act: -0.1700
Data Index: 4689075 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.6703. Min Act: -0.1700
Data Index: 2152784 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.6703. Min Act: -0.1700
Data Index: 1154307 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.6703. Min Act: -0.1700
Data Index: 5780055 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.6391. Min Act: -0.1700
Data Index: 4039415 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.6078. Min Act: -0.1700
Data Index: 7431874 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7328. Min Range: -6.7328
Max Act: 5.6391. Min Act: -0.1700
Data Index: 7881980 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19