Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 705 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.9621. Min Act: -0.1700
Data Index: 695774 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.9308. Min Act: -0.1700
Data Index: 3431529 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.8996. Min Act: -0.1700
Data Index: 6964318 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.8371. Min Act: -0.1700
Data Index: 3834980 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.8371. Min Act: -0.1700
Data Index: 2179684 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.8058. Min Act: -0.1700
Data Index: 5278870 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.8058. Min Act: -0.1700
Data Index: 4482172 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7433. Min Act: -0.1700
Data Index: 3444953 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.8058. Min Act: -0.1700
Data Index: 4181110 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7121. Min Act: -0.1700
Data Index: 3927470 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7433. Min Act: -0.1700
Data Index: 6212688 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7433. Min Act: -0.1700
Data Index: 4013754 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7121. Min Act: -0.1700
Data Index: 6724642 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7121. Min Act: -0.1700
Data Index: 7504105 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7433. Min Act: -0.1700
Data Index: 2013651 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7121. Min Act: -0.1700
Data Index: 1227149 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7433. Min Act: -0.1700
Data Index: 3645250 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6808. Min Act: -0.1700
Data Index: 1586370 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6808. Min Act: -0.1700
Data Index: 4721400 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7121. Min Act: -0.1700
Data Index: 3152879 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19