Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 486 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.7805. Min Act: -0.1700
Data Index: 8221252 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.7805. Min Act: -0.1700
Data Index: 4916341 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.6868. Min Act: -0.1700
Data Index: 6595171 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.6243. Min Act: -0.1700
Data Index: 6874923 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.6243. Min Act: -0.1700
Data Index: 5202579 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.5305. Min Act: -0.1700
Data Index: 4876004 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.6243. Min Act: -0.1700
Data Index: 4236340 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.5618. Min Act: -0.1700
Data Index: 1917140 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.5618. Min Act: -0.1700
Data Index: 4929630 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.5305. Min Act: -0.1700
Data Index: 2550641 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.4993. Min Act: -0.1700
Data Index: 8484731 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.4993. Min Act: -0.1700
Data Index: 3984756 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.3743. Min Act: -0.1700
Data Index: 982843 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.5305. Min Act: -0.1700
Data Index: 774137 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.4680. Min Act: -0.1700
Data Index: 7731854 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.4680. Min Act: -0.1700
Data Index: 4728780 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.4680. Min Act: -0.1700
Data Index: 3553324 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.4680. Min Act: -0.1700
Data Index: 784197 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.4993. Min Act: -0.1700
Data Index: 3237258 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7805. Min Range: -5.7805
Max Act: 5.4680. Min Act: -0.1700
Data Index: 3404320 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19