Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4327 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.3515. Min Act: -0.1700
Data Index: 7859225 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.2890. Min Act: -0.1700
Data Index: 6866732 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.2265. Min Act: -0.1700
Data Index: 3795761 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.2578. Min Act: -0.1700
Data Index: 6828318 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.2265. Min Act: -0.1700
Data Index: 5959003 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1953. Min Act: -0.1700
Data Index: 782811 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1328. Min Act: -0.1700
Data Index: 979871 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1640. Min Act: -0.1700
Data Index: 4374933 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1328. Min Act: -0.1700
Data Index: 8288745 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1015. Min Act: -0.1700
Data Index: 631086 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1015. Min Act: -0.1700
Data Index: 7870249 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1015. Min Act: -0.1700
Data Index: 3116315 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1015. Min Act: -0.1700
Data Index: 690057 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0703. Min Act: -0.1700
Data Index: 5019803 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 4485329 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0078. Min Act: -0.1700
Data Index: 4120484 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0078. Min Act: -0.1700
Data Index: 7859226 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 6628801 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 79853 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 5546607 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19