Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0321. Min Range: -3.0321
Max Act: 3.0321. Min Act: -0.1700
Data Index: 1854192 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0321. Min Range: -3.0321
Max Act: 3.0163. Min Act: -0.1700
Data Index: 8233697 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0321. Min Range: -3.0321
Max Act: 3.0163. Min Act: -0.1700
Data Index: 5398464 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.9689. Min Act: -0.1700
Data Index: 7051194 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.9531. Min Act: -0.1700
Data Index: 5402009 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.9531. Min Act: -0.1700
Data Index: 546126 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.9372. Min Act: -0.1700
Data Index: 6489187 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.9372. Min Act: -0.1700
Data Index: 6852971 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.9214. Min Act: -0.1700
Data Index: 7567093 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.9055. Min Act: -0.1700
Data Index: 7567092 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.9055. Min Act: -0.1700
Data Index: 7567097 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.8897. Min Act: -0.1700
Data Index: 6536515 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.8579. Min Act: -0.1700
Data Index: 5040445 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.8738. Min Act: -0.1700
Data Index: 6513736 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.8897. Min Act: -0.1700
Data Index: 4480786 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.8738. Min Act: -0.1700
Data Index: 4465758 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.8738. Min Act: -0.1700
Data Index: 8239471 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.8579. Min Act: -0.1700
Data Index: 8225172 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.8579. Min Act: -0.1700
Data Index: 1604615 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0321. Min Range: -3.0321
Max Act: 2.8420. Min Act: -0.1700
Data Index: 3639947 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19