Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2503. Min Range: -6.2503
Max Act: 6.2503. Min Act: -0.1700
Data Index: 1709487 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2503. Min Range: -6.2503
Max Act: 6.1878. Min Act: -0.1700
Data Index: 416017 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2503. Min Range: -6.2503
Max Act: 6.1253. Min Act: -0.1700
Data Index: 4452825 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2503. Min Range: -6.2503
Max Act: 6.0628. Min Act: -0.1700
Data Index: 7168157 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2503. Min Range: -6.2503
Max Act: 6.0941. Min Act: -0.1700
Data Index: 5816337 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2503. Min Range: -6.2503
Max Act: 6.0628. Min Act: -0.1700
Data Index: 2375879 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.9691. Min Act: -0.1700
Data Index: 3068055 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2503. Min Range: -6.2503
Max Act: 6.0003. Min Act: -0.1700
Data Index: 7852197 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2503. Min Range: -6.2503
Max Act: 6.0003. Min Act: -0.1700
Data Index: 4096541 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.9691. Min Act: -0.1700
Data Index: 8778233 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.9691. Min Act: -0.1700
Data Index: 3869053 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2503. Min Range: -6.2503
Max Act: 6.0003. Min Act: -0.1700
Data Index: 1019786 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.9691. Min Act: -0.1700
Data Index: 6312478 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.9378. Min Act: -0.1700
Data Index: 3773356 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.9378. Min Act: -0.1700
Data Index: 8286948 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.9066. Min Act: -0.1700
Data Index: 6066142 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.9066. Min Act: -0.1700
Data Index: 3006464 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.8753. Min Act: -0.1700
Data Index: 3964403 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.8753. Min Act: -0.1700
Data Index: 1899101 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2503. Min Range: -6.2503
Max Act: 5.8753. Min Act: -0.1700
Data Index: 4848328 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19