Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.9019. Min Act: -0.1700
Data Index: 5901082 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.9019. Min Act: -0.1700
Data Index: 1172816 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8702. Min Act: -0.1700
Data Index: 5451591 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8702. Min Act: -0.1700
Data Index: 563325 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8702. Min Act: -0.1700
Data Index: 4137344 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8384. Min Act: -0.1700
Data Index: 154194 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8384. Min Act: -0.1700
Data Index: 2889702 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8384. Min Act: -0.1700
Data Index: 5967111 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8384. Min Act: -0.1700
Data Index: 7314843 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8225. Min Act: -0.1700
Data Index: 582307 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8225. Min Act: -0.1700
Data Index: 5661983 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8225. Min Act: -0.1700
Data Index: 207562 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8225. Min Act: -0.1700
Data Index: 6663997 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8066. Min Act: -0.1700
Data Index: 4555767 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8066. Min Act: -0.1700
Data Index: 1295298 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8066. Min Act: -0.1700
Data Index: 7876649 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8066. Min Act: -0.1700
Data Index: 1114542 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8066. Min Act: -0.1700
Data Index: 1880435 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.7907. Min Act: -0.1700
Data Index: 1683227 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9019. Min Range: -2.9019
Max Act: 2.8066. Min Act: -0.1700
Data Index: 5455672 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19