Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4083 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.6379. Min Act: -0.1700
Data Index: 3950518 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.6692. Min Act: -0.1700
Data Index: 3936434 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.6067. Min Act: -0.1700
Data Index: 8744400 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.5442. Min Act: -0.1700
Data Index: 5207944 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.5129. Min Act: -0.1700
Data Index: 8384846 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.5129. Min Act: -0.1700
Data Index: 1438472 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4817. Min Act: -0.1700
Data Index: 6505490 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.5442. Min Act: -0.1700
Data Index: 7040858 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.5129. Min Act: -0.1700
Data Index: 7342476 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4504. Min Act: -0.1700
Data Index: 8759154 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4817. Min Act: -0.1700
Data Index: 4403751 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4192. Min Act: -0.1700
Data Index: 2720810 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4192. Min Act: -0.1700
Data Index: 8264668 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4504. Min Act: -0.1700
Data Index: 3541854 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4192. Min Act: -0.1700
Data Index: 1221950 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4504. Min Act: -0.1700
Data Index: 4371111 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4192. Min Act: -0.1700
Data Index: 6797333 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4192. Min Act: -0.1700
Data Index: 351411 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4504. Min Act: -0.1700
Data Index: 6912880 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.3879. Min Act: -0.1700
Data Index: 4815082 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19