Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2350 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0899. Min Range: -5.0899
Max Act: 5.0899. Min Act: -0.1700
Data Index: 5048126 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.9962. Min Act: -0.1700
Data Index: 7679261 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.9649. Min Act: -0.1700
Data Index: 7170667 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.9649. Min Act: -0.1700
Data Index: 1719020 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.9649. Min Act: -0.1700
Data Index: 413428 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.9024. Min Act: -0.1700
Data Index: 7215464 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.9649. Min Act: -0.1700
Data Index: 4564782 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.9024. Min Act: -0.1700
Data Index: 7338192 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.9024. Min Act: -0.1700
Data Index: 8321912 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.8399. Min Act: -0.1700
Data Index: 2212300 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.8712. Min Act: -0.1700
Data Index: 6906689 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.8712. Min Act: -0.1700
Data Index: 5530720 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.8399. Min Act: -0.1700
Data Index: 5645734 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.8399. Min Act: -0.1700
Data Index: 1524097 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.8087. Min Act: -0.1700
Data Index: 141147 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.8087. Min Act: -0.1700
Data Index: 7447426 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.8087. Min Act: -0.1700
Data Index: 400970 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.7774. Min Act: -0.1700
Data Index: 2102640 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.7462. Min Act: -0.1700
Data Index: 4796186 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0899. Min Range: -5.0899
Max Act: 4.7774. Min Act: -0.1700
Data Index: 7516742 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19