Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.9085. Min Act: -0.1700
Data Index: 8308317 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.9085. Min Act: -0.1700
Data Index: 4977973 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.7835. Min Act: -0.1700
Data Index: 39859 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.7523. Min Act: -0.1700
Data Index: 3664809 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.6585. Min Act: -0.1700
Data Index: 5135000 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.6273. Min Act: -0.1700
Data Index: 1962437 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.5960. Min Act: -0.1700
Data Index: 373734 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.5960. Min Act: -0.1700
Data Index: 7803918 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.5648. Min Act: -0.1700
Data Index: 8088755 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.5023. Min Act: -0.1700
Data Index: 7908361 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.5023. Min Act: -0.1700
Data Index: 4977975 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.5023. Min Act: -0.1700
Data Index: 8428566 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.4710. Min Act: -0.1700
Data Index: 3190025 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.4710. Min Act: -0.1700
Data Index: 7334917 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.4710. Min Act: -0.1700
Data Index: 4463629 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.4710. Min Act: -0.1700
Data Index: 3321165 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.4085. Min Act: -0.1700
Data Index: 2505910 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.4398. Min Act: -0.1700
Data Index: 373741 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.3773. Min Act: -0.1700
Data Index: 3426867 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9085. Min Range: -6.9085
Max Act: 6.3773. Min Act: -0.1700
Data Index: 2373641 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19