Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3819 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.4772. Min Act: -0.1700
Data Index: 603098 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.2897. Min Act: -0.1700
Data Index: 4417279 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.2897. Min Act: -0.1700
Data Index: 3503313 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.2585. Min Act: -0.1700
Data Index: 2031039 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.2585. Min Act: -0.1700
Data Index: 8073784 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.2272. Min Act: -0.1700
Data Index: 4734142 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.2272. Min Act: -0.1700
Data Index: 2772449 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1960. Min Act: -0.1700
Data Index: 5517824 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1960. Min Act: -0.1700
Data Index: 2499695 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1960. Min Act: -0.1700
Data Index: 3214303 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1960. Min Act: -0.1700
Data Index: 5154305 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1960. Min Act: -0.1700
Data Index: 5484565 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1960. Min Act: -0.1700
Data Index: 4730389 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1960. Min Act: -0.1700
Data Index: 3407341 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1647. Min Act: -0.1700
Data Index: 7136218 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1335. Min Act: -0.1700
Data Index: 661852 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1647. Min Act: -0.1700
Data Index: 5660160 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1647. Min Act: -0.1700
Data Index: 3195172 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1647. Min Act: -0.1700
Data Index: 2238547 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4772. Min Range: -5.4772
Max Act: 5.1647. Min Act: -0.1700
Data Index: 6340517 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19