Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4383 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.4522. Min Act: -0.1700
Data Index: 4363607 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.3272. Min Act: -0.1700
Data Index: 4391238 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.2022. Min Act: -0.1700
Data Index: 6056589 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0772. Min Act: -0.1700
Data Index: 4078909 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0459. Min Act: -0.1700
Data Index: 6281666 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0147. Min Act: -0.1700
Data Index: 1196878 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0147. Min Act: -0.1700
Data Index: 3263764 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0147. Min Act: -0.1700
Data Index: 2500889 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0147. Min Act: -0.1700
Data Index: 7785714 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9834. Min Act: -0.1699
Data Index: 8038041 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4522. Min Range: -5.4522
Max Act: 5.0147. Min Act: -0.1700
Data Index: 2130087 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9522. Min Act: -0.1700
Data Index: 4743404 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9522. Min Act: -0.1700
Data Index: 5061600 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.9209. Min Act: -0.1700
Data Index: 2130086 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.8897. Min Act: -0.1700
Data Index: 6857932 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.8897. Min Act: -0.1700
Data Index: 8274367 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.8897. Min Act: -0.1700
Data Index: 7825236 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.8897. Min Act: -0.1700
Data Index: 1262727 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.8584. Min Act: -0.1700
Data Index: 6388547 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4522. Min Range: -5.4522
Max Act: 4.8584. Min Act: -0.1700
Data Index: 4389831 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19