Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.8017. Min Act: -0.1700
Data Index: 3924634 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.7080. Min Act: -0.1700
Data Index: 8185844 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.6455. Min Act: -0.1700
Data Index: 3649210 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.6455. Min Act: -0.1700
Data Index: 3725122 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.6142. Min Act: -0.1700
Data Index: 1615795 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.6142. Min Act: -0.1700
Data Index: 2380709 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.5830. Min Act: -0.1700
Data Index: 8578980 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.5517. Min Act: -0.1700
Data Index: 16531 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.5205. Min Act: -0.1700
Data Index: 1107017 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.5517. Min Act: -0.1700
Data Index: 7912411 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.5205. Min Act: -0.1700
Data Index: 5903960 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.4892. Min Act: -0.1700
Data Index: 8074235 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.5205. Min Act: -0.1700
Data Index: 4370206 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.5205. Min Act: -0.1700
Data Index: 7378527 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.5205. Min Act: -0.1700
Data Index: 6725951 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.5205. Min Act: -0.1700
Data Index: 8389522 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.5205. Min Act: -0.1700
Data Index: 4947510 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.4892. Min Act: -0.1700
Data Index: 96088 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.4892. Min Act: -0.1700
Data Index: 5710549 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8017. Min Range: -5.8017
Max Act: 5.4892. Min Act: -0.1700
Data Index: 2792600 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19