Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2666 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0826. Min Range: -5.0826
Max Act: 5.0826. Min Act: -0.1700
Data Index: 6728159 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0826. Min Range: -5.0826
Max Act: 5.0514. Min Act: -0.1700
Data Index: 761587 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0826. Min Range: -5.0826
Max Act: 5.0514. Min Act: -0.1700
Data Index: 3901647 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.9264. Min Act: -0.1700
Data Index: 6027529 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.8014. Min Act: -0.1699
Data Index: 8281166 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.8014. Min Act: -0.1700
Data Index: 1918518 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.7701. Min Act: -0.1700
Data Index: 5887061 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.8014. Min Act: -0.1700
Data Index: 3779100 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.7389. Min Act: -0.1700
Data Index: 2248993 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.7389. Min Act: -0.1700
Data Index: 4816163 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.6451. Min Act: -0.1700
Data Index: 7466387 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.6764. Min Act: -0.1700
Data Index: 4761923 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.6451. Min Act: -0.1700
Data Index: 6827291 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.6764. Min Act: -0.1700
Data Index: 846691 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.6451. Min Act: -0.1700
Data Index: 2954533 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.5826. Min Act: -0.1700
Data Index: 2750064 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.6139. Min Act: -0.1700
Data Index: 1918519 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.5826. Min Act: -0.1700
Data Index: 3919657 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.5514. Min Act: -0.1700
Data Index: 7135542 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0826. Min Range: -5.0826
Max Act: 4.5514. Min Act: -0.1700
Data Index: 3877743 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19