Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.2011. Min Act: -0.1700
Data Index: 1302901 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.2011. Min Act: -0.1700
Data Index: 4870131 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.1074. Min Act: -0.1700
Data Index: 2824210 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.1074. Min Act: -0.1700
Data Index: 1855295 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.0136. Min Act: -0.1700
Data Index: 7299615 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.0136. Min Act: -0.1700
Data Index: 5044163 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9823. Min Act: -0.1700
Data Index: 155627 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9198. Min Act: -0.1700
Data Index: 6488208 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9511. Min Act: -0.1700
Data Index: 197247 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9198. Min Act: -0.1700
Data Index: 4870132 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9198. Min Act: -0.1700
Data Index: 4470817 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9198. Min Act: -0.1700
Data Index: 1401339 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9511. Min Act: -0.1700
Data Index: 2104982 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.8886. Min Act: -0.1700
Data Index: 916321 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9198. Min Act: -0.1700
Data Index: 3287480 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.8886. Min Act: -0.1700
Data Index: 1693950 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.8886. Min Act: -0.1700
Data Index: 3071187 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.8886. Min Act: -0.1700
Data Index: 2491591 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.8573. Min Act: -0.1700
Data Index: 5515014 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.8886. Min Act: -0.1700
Data Index: 6103932 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19