Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 393 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.9675. Min Act: -0.1700
Data Index: 8388592 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.9362. Min Act: -0.1700
Data Index: 3435207 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.9050. Min Act: -0.1700
Data Index: 6936859 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.8737. Min Act: -0.1700
Data Index: 2601434 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.8112. Min Act: -0.1700
Data Index: 5021862 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.8425. Min Act: -0.1700
Data Index: 2892630 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.7800. Min Act: -0.1700
Data Index: 6926971 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.7487. Min Act: -0.1700
Data Index: 4533602 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.7487. Min Act: -0.1700
Data Index: 4320472 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.7487. Min Act: -0.1700
Data Index: 5018932 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.7175. Min Act: -0.1700
Data Index: 7689822 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.6862. Min Act: -0.1700
Data Index: 404328 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.6862. Min Act: -0.1700
Data Index: 6864127 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.6862. Min Act: -0.1700
Data Index: 7068036 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.6862. Min Act: -0.1700
Data Index: 4700445 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.6862. Min Act: -0.1700
Data Index: 8248983 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.6862. Min Act: -0.1700
Data Index: 7840000 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.6550. Min Act: -0.1700
Data Index: 4087149 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.6550. Min Act: -0.1700
Data Index: 4325315 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9675. Min Range: -5.9675
Max Act: 5.6550. Min Act: -0.1700
Data Index: 313326 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19