Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1994 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.3637. Min Act: -0.1700
Data Index: 307515 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1762. Min Act: -0.1700
Data Index: 6029348 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.2075. Min Act: -0.1700
Data Index: 137941 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1762. Min Act: -0.1700
Data Index: 23396 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1137. Min Act: -0.1700
Data Index: 656155 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1450. Min Act: -0.1700
Data Index: 5910939 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1137. Min Act: -0.1700
Data Index: 744499 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1137. Min Act: -0.1700
Data Index: 1937602 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0825. Min Act: -0.1700
Data Index: 8024299 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1137. Min Act: -0.1700
Data Index: 5643866 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0825. Min Act: -0.1700
Data Index: 6940014 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0512. Min Act: -0.1700
Data Index: 473111 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0200. Min Act: -0.1700
Data Index: 7640545 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9887. Min Act: -0.1700
Data Index: 1052351 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9887. Min Act: -0.1700
Data Index: 951398 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9887. Min Act: -0.1700
Data Index: 5179049 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9575. Min Act: -0.1700
Data Index: 700773 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9575. Min Act: -0.1700
Data Index: 5262503 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9262. Min Act: -0.1700
Data Index: 6763516 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9887. Min Act: -0.1700
Data Index: 3837777 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19