Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1509. Min Range: -6.1509
Max Act: 6.1509. Min Act: -0.1700
Data Index: 8498153 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1509. Min Range: -6.1509
Max Act: 6.0571. Min Act: -0.1700
Data Index: 4188176 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1509. Min Range: -6.1509
Max Act: 6.0884. Min Act: -0.1700
Data Index: 334887 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1509. Min Range: -6.1509
Max Act: 6.0884. Min Act: -0.1700
Data Index: 4844460 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1509. Min Range: -6.1509
Max Act: 6.0571. Min Act: -0.1700
Data Index: 8498150 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.9946. Min Act: -0.1700
Data Index: 1361096 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.9946. Min Act: -0.1700
Data Index: 6867157 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.9946. Min Act: -0.1700
Data Index: 3658961 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.9634. Min Act: -0.1700
Data Index: 3733749 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.9321. Min Act: -0.1700
Data Index: 5340270 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.9321. Min Act: -0.1700
Data Index: 7067011 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.9009. Min Act: -0.1700
Data Index: 7016047 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.9009. Min Act: -0.1700
Data Index: 4228795 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.9009. Min Act: -0.1700
Data Index: 6938972 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.9321. Min Act: -0.1700
Data Index: 6905715 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.8696. Min Act: -0.1700
Data Index: 1887266 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.8696. Min Act: -0.1700
Data Index: 5209596 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.8696. Min Act: -0.1700
Data Index: 8503292 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.8696. Min Act: -0.1700
Data Index: 3180768 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1509. Min Range: -6.1509
Max Act: 5.8696. Min Act: -0.1700
Data Index: 8590759 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19