Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 837 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1675. Min Range: -9.1675
Max Act: 9.1675. Min Act: -0.1700
Data Index: 6301296 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1675. Min Range: -9.1675
Max Act: 9.1675. Min Act: -0.1700
Data Index: 7469521 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1675. Min Range: -9.1675
Max Act: 9.1050. Min Act: -0.1700
Data Index: 8220295 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1675. Min Range: -9.1675
Max Act: 9.1050. Min Act: -0.1700
Data Index: 69866 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1675. Min Range: -9.1675
Max Act: 9.1050. Min Act: -0.1700
Data Index: 6409616 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1675. Min Range: -9.1675
Max Act: 9.1050. Min Act: -0.1700
Data Index: 8235459 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1675. Min Range: -9.1675
Max Act: 9.0425. Min Act: -0.1700
Data Index: 7409716 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.9800. Min Act: -0.1700
Data Index: 4790865 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.9800. Min Act: -0.1700
Data Index: 7314446 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.9800. Min Act: -0.1700
Data Index: 6789657 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.9800. Min Act: -0.1700
Data Index: 8753912 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.9175. Min Act: -0.1700
Data Index: 917809 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.9175. Min Act: -0.1700
Data Index: 906222 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.8550. Min Act: -0.1700
Data Index: 4867895 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.8550. Min Act: -0.1700
Data Index: 5086618 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.8550. Min Act: -0.1700
Data Index: 2237929 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.8550. Min Act: -0.1700
Data Index: 5260098 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.8550. Min Act: -0.1700
Data Index: 7889951 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.8550. Min Act: -0.1700
Data Index: 1652704 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1675. Min Range: -9.1675
Max Act: 8.7925. Min Act: -0.1700
Data Index: 894402 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19