Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.1412. Min Act: -0.1700
Data Index: 7880931 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.1078. Min Act: -0.1700
Data Index: 5859475 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.1078. Min Act: -0.1700
Data Index: 7941165 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0743. Min Act: -0.1700
Data Index: 1190359 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0575. Min Act: -0.1700
Data Index: 8281736 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0407. Min Act: -0.1700
Data Index: 3738057 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0407. Min Act: -0.1700
Data Index: 388396 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0407. Min Act: -0.1700
Data Index: 3859574 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0407. Min Act: -0.1700
Data Index: 8125980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0069. Min Act: -0.1700
Data Index: 4027310 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0069. Min Act: -0.1700
Data Index: 212056 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0238. Min Act: -0.1700
Data Index: 2145134 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0238. Min Act: -0.1700
Data Index: 8560335 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0069. Min Act: -0.1700
Data Index: 8057699 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0238. Min Act: -0.1700
Data Index: 1282768 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1412. Min Range: -2.1412
Max Act: 1.9900. Min Act: -0.1700
Data Index: 4094848 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0069. Min Act: -0.1696
Data Index: 6067599 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1412. Min Range: -2.1412
Max Act: 1.9900. Min Act: -0.1700
Data Index: 6628127 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1412. Min Range: -2.1412
Max Act: 1.9900. Min Act: -0.1700
Data Index: 5216712 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1412. Min Range: -2.1412
Max Act: 2.0069. Min Act: -0.1700
Data Index: 7265095 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19