Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.9675. Min Act: -0.1700
Data Index: 1337548 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.9675. Min Act: -0.1700
Data Index: 6563460 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.9050. Min Act: -0.1700
Data Index: 2203897 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.9050. Min Act: -0.1700
Data Index: 8759387 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8738. Min Act: -0.1700
Data Index: 4714332 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8738. Min Act: -0.1700
Data Index: 5731899 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8738. Min Act: -0.1700
Data Index: 5357142 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8738. Min Act: -0.1700
Data Index: 1031312 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8738. Min Act: -0.1700
Data Index: 5003361 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8738. Min Act: -0.1700
Data Index: 8527648 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8738. Min Act: -0.1700
Data Index: 2351921 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8738. Min Act: -0.1700
Data Index: 1527878 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8738. Min Act: -0.1700
Data Index: 776167 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8425. Min Act: -0.1700
Data Index: 6228839 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8425. Min Act: -0.1700
Data Index: 5844370 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8425. Min Act: -0.1700
Data Index: 8156157 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8425. Min Act: -0.1700
Data Index: 1036926 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8113. Min Act: -0.1700
Data Index: 6945800 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8113. Min Act: -0.1700
Data Index: 1390368 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9675. Min Range: -4.9675
Max Act: 4.8113. Min Act: -0.1700
Data Index: 7893825 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19