Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 666 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.5770. Min Act: -0.1700
Data Index: 6760975 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.4518. Min Act: -0.1700
Data Index: 3142589 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.4518. Min Act: -0.1700
Data Index: 4046905 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.4204. Min Act: -0.1700
Data Index: 857888 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.4204. Min Act: -0.1700
Data Index: 7115758 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3891. Min Act: -0.1700
Data Index: 3419631 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3734. Min Act: -0.1700
Data Index: 6068483 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3577. Min Act: -0.1700
Data Index: 1240340 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3263. Min Act: -0.1700
Data Index: 6048397 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3420. Min Act: -0.1700
Data Index: 8453441 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3420. Min Act: -0.1700
Data Index: 7564455 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3263. Min Act: -0.1700
Data Index: 6484448 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3106. Min Act: -0.1700
Data Index: 4166142 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3106. Min Act: -0.1700
Data Index: 7593124 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3106. Min Act: -0.1700
Data Index: 5923192 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3106. Min Act: -0.1700
Data Index: 6080372 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.3106. Min Act: -0.1700
Data Index: 6545007 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.2949. Min Act: -0.1700
Data Index: 6700970 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.2949. Min Act: -0.1700
Data Index: 6700973 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5770. Min Range: -3.5770
Max Act: 3.2792. Min Act: -0.1700
Data Index: 4121995 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19