Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2610 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0044. Min Range: -4.0044
Max Act: 4.0044. Min Act: -0.1700
Data Index: 6174086 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.8168. Min Act: -0.1700
Data Index: 435959 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.8481. Min Act: -0.1700
Data Index: 7414797 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.7699. Min Act: -0.1700
Data Index: 6138191 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.7699. Min Act: -0.1700
Data Index: 6927496 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.7386. Min Act: -0.1700
Data Index: 8042883 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.7542. Min Act: -0.1700
Data Index: 7524780 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.7699. Min Act: -0.1700
Data Index: 8712595 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.7386. Min Act: -0.1700
Data Index: 4786022 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.7229. Min Act: -0.1700
Data Index: 4482799 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.7229. Min Act: -0.1700
Data Index: 5344662 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.6917. Min Act: -0.1700
Data Index: 5655894 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.7073. Min Act: -0.1700
Data Index: 6380004 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.7073. Min Act: -0.1700
Data Index: 2744069 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.6917. Min Act: -0.1700
Data Index: 558377 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.6760. Min Act: -0.1700
Data Index: 5347847 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.6917. Min Act: -0.1700
Data Index: 2638397 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.6917. Min Act: -0.1700
Data Index: 7337251 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.6447. Min Act: -0.1700
Data Index: 5643683 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0044. Min Range: -4.0044
Max Act: 3.6760. Min Act: -0.1700
Data Index: 4364479 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19