Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0996. Min Range: -5.0996
Max Act: 5.0683. Min Act: -0.1700
Data Index: 5807255 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0996. Min Range: -5.0996
Max Act: 5.0996. Min Act: -0.1700
Data Index: 4425207 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0996. Min Range: -5.0996
Max Act: 5.0996. Min Act: -0.1700
Data Index: 600259 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0996. Min Range: -5.0996
Max Act: 5.0683. Min Act: -0.1700
Data Index: 7637112 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0996. Min Range: -5.0996
Max Act: 5.0683. Min Act: -0.1700
Data Index: 369544 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0996. Min Range: -5.0996
Max Act: 5.0371. Min Act: -0.1700
Data Index: 5587564 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0996. Min Range: -5.0996
Max Act: 5.0371. Min Act: -0.1700
Data Index: 4559563 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.9121. Min Act: -0.1700
Data Index: 3567261 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.9121. Min Act: -0.1700
Data Index: 2077413 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.8808. Min Act: -0.1700
Data Index: 6833874 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.8808. Min Act: -0.1700
Data Index: 6002321 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.8808. Min Act: -0.1700
Data Index: 7547224 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.8496. Min Act: -0.1700
Data Index: 6946737 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.8496. Min Act: -0.1700
Data Index: 4453878 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.8496. Min Act: -0.1700
Data Index: 6769712 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.8183. Min Act: -0.1700
Data Index: 4494770 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.8183. Min Act: -0.1700
Data Index: 707260 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.8183. Min Act: -0.1700
Data Index: 7856607 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.8183. Min Act: -0.1700
Data Index: 2032217 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0996. Min Range: -5.0996
Max Act: 4.7871. Min Act: -0.1700
Data Index: 900987 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19