Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3114 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.6637. Min Act: -0.1700
Data Index: 3330832 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.6637. Min Act: -0.1700
Data Index: 65916 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.6637. Min Act: -0.1700
Data Index: 1505925 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.6012. Min Act: -0.1700
Data Index: 946912 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.5387. Min Act: -0.1700
Data Index: 3407632 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4762. Min Act: -0.1700
Data Index: 1677749 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.5387. Min Act: -0.1700
Data Index: 8210631 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4762. Min Act: -0.1700
Data Index: 47733 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4762. Min Act: -0.1700
Data Index: 3017945 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.5387. Min Act: -0.1700
Data Index: 2662576 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4762. Min Act: -0.1700
Data Index: 7391944 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4762. Min Act: -0.1700
Data Index: 1570176 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4762. Min Act: -0.1700
Data Index: 2617437 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4137. Min Act: -0.1700
Data Index: 6327448 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4762. Min Act: -0.1700
Data Index: 5819051 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.5387. Min Act: -0.1700
Data Index: 8825692 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4137. Min Act: -0.1700
Data Index: 343070 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.3512. Min Act: -0.1700
Data Index: 6945192 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4137. Min Act: -0.1700
Data Index: 1585034 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6637. Min Range: -8.6637
Max Act: 8.4137. Min Act: -0.1700
Data Index: 6121439 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19