Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1308 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.5772. Min Act: -0.1700
Data Index: 3233935 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.5147. Min Act: -0.1700
Data Index: 5312307 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.5147. Min Act: -0.1700
Data Index: 8009626 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.5147. Min Act: -0.1700
Data Index: 8620938 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.4834. Min Act: -0.1700
Data Index: 5382833 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.4834. Min Act: -0.1700
Data Index: 3194311 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.4522. Min Act: -0.1700
Data Index: 1635642 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.4522. Min Act: -0.1700
Data Index: 264497 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.4522. Min Act: -0.1700
Data Index: 2968078 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.4209. Min Act: -0.1700
Data Index: 7078159 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.4209. Min Act: -0.1700
Data Index: 6115467 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.4209. Min Act: -0.1700
Data Index: 4129190 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.3897. Min Act: -0.1700
Data Index: 7627873 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.3897. Min Act: -0.1700
Data Index: 678384 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.3897. Min Act: -0.1700
Data Index: 2906536 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.3584. Min Act: -0.1700
Data Index: 7949570 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.3584. Min Act: -0.1700
Data Index: 1946217 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.3584. Min Act: -0.1700
Data Index: 546179 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.3584. Min Act: -0.1700
Data Index: 3256403 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5772. Min Range: -6.5772
Max Act: 6.3584. Min Act: -0.1700
Data Index: 7213716 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19