Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4669 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0583. Min Range: -3.0583
Max Act: 3.0583. Min Act: -0.1700
Data Index: 851217 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0583. Min Range: -3.0583
Max Act: 3.0425. Min Act: -0.1700
Data Index: 5866325 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.9318. Min Act: -0.1700
Data Index: 3852422 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.9002. Min Act: -0.1700
Data Index: 1825998 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.8843. Min Act: -0.1700
Data Index: 6253394 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.8843. Min Act: -0.1700
Data Index: 1852729 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.8207. Min Act: -0.1700
Data Index: 6715044 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.8207. Min Act: -0.1700
Data Index: 5897551 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.8048. Min Act: -0.1700
Data Index: 6935571 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.8048. Min Act: -0.1700
Data Index: 3563241 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.7889. Min Act: -0.1700
Data Index: 6751688 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.7730. Min Act: -0.1700
Data Index: 5129229 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.7570. Min Act: -0.1700
Data Index: 37626 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.7570. Min Act: -0.1700
Data Index: 5959391 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.7570. Min Act: -0.1700
Data Index: 4588891 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.7570. Min Act: -0.1700
Data Index: 6731498 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.7410. Min Act: -0.1700
Data Index: 5155530 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.7410. Min Act: -0.1700
Data Index: 2275161 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.7410. Min Act: -0.1700
Data Index: 5502061 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0583. Min Range: -3.0583
Max Act: 2.7410. Min Act: -0.1700
Data Index: 5151898 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19