Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2044 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.1957. Min Act: -0.1700
Data Index: 4328403 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.1012. Min Act: -0.1700
Data Index: 7863646 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0855. Min Act: -0.1700
Data Index: 5403248 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.1012. Min Act: -0.1700
Data Index: 2157786 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.1012. Min Act: -0.1700
Data Index: 4291917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0697. Min Act: -0.1700
Data Index: 8081073 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0697. Min Act: -0.1700
Data Index: 337410 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0697. Min Act: -0.1700
Data Index: 3235494 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0697. Min Act: -0.1700
Data Index: 4885571 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0697. Min Act: -0.1700
Data Index: 8055982 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0697. Min Act: -0.1700
Data Index: 6872557 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0697. Min Act: -0.1700
Data Index: 1894704 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0539. Min Act: -0.1700
Data Index: 1660577 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0697. Min Act: -0.1700
Data Index: 5702412 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0539. Min Act: -0.1700
Data Index: 1140512 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0539. Min Act: -0.1700
Data Index: 3328341 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0539. Min Act: -0.1700
Data Index: 2507359 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0539. Min Act: -0.1700
Data Index: 1024048 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0539. Min Act: -0.1700
Data Index: 1057314 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0539. Min Act: -0.1700
Data Index: 2700305 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19