Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4546 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.5976. Min Act: -0.1700
Data Index: 7639966 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.5664. Min Act: -0.1700
Data Index: 8079759 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.5039. Min Act: -0.1700
Data Index: 7793368 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.5039. Min Act: -0.1700
Data Index: 3035662 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.4726. Min Act: -0.1700
Data Index: 7474977 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.4726. Min Act: -0.1700
Data Index: 4616048 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.4726. Min Act: -0.1700
Data Index: 1880285 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.4726. Min Act: -0.1700
Data Index: 4292893 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.4726. Min Act: -0.1699
Data Index: 6771732 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.4414. Min Act: -0.1700
Data Index: 6585893 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.4101. Min Act: -0.1700
Data Index: 8558340 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.3789. Min Act: -0.1700
Data Index: 6700364 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.3476. Min Act: -0.1700
Data Index: 6680406 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.4101. Min Act: -0.1700
Data Index: 2395810 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.3476. Min Act: -0.1700
Data Index: 4165026 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.3476. Min Act: -0.1700
Data Index: 725392 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.3164. Min Act: -0.1699
Data Index: 2046590 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.2851. Min Act: -0.1700
Data Index: 6787942 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.2539. Min Act: -0.1700
Data Index: 5923855 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5976. Min Range: -5.5976
Max Act: 5.2539. Min Act: -0.1700
Data Index: 6155783 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19