Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.6265. Min Act: -0.1700
Data Index: 4764987 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.5328. Min Act: -0.1700
Data Index: 3417726 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.5328. Min Act: -0.1700
Data Index: 728891 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.5328. Min Act: -0.1700
Data Index: 4760565 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.4390. Min Act: -0.1700
Data Index: 7996107 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.4078. Min Act: -0.1700
Data Index: 3218697 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.4078. Min Act: -0.1700
Data Index: 5415297 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.4078. Min Act: -0.1700
Data Index: 671767 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.3765. Min Act: -0.1700
Data Index: 3635890 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.4078. Min Act: -0.1700
Data Index: 5602194 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.3765. Min Act: -0.1700
Data Index: 7752399 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.4078. Min Act: -0.1700
Data Index: 3849008 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.3765. Min Act: -0.1700
Data Index: 2029870 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.3453. Min Act: -0.1700
Data Index: 2203823 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.3453. Min Act: -0.1700
Data Index: 6050653 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.2828. Min Act: -0.1700
Data Index: 3328862 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.3140. Min Act: -0.1700
Data Index: 1917199 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.2515. Min Act: -0.1700
Data Index: 1807033 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.3140. Min Act: -0.1700
Data Index: 3500109 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6265. Min Range: -6.6265
Max Act: 6.2515. Min Act: -0.1700
Data Index: 262236 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19