Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.5874. Min Act: -0.1700
Data Index: 3878181 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.3374. Min Act: -0.1700
Data Index: 2909794 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.2749. Min Act: -0.1700
Data Index: 7259803 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.1811. Min Act: -0.1700
Data Index: 2244877 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.1811. Min Act: -0.1700
Data Index: 6352094 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.1811. Min Act: -0.1700
Data Index: 8016434 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.1499. Min Act: -0.1700
Data Index: 7023545 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.1186. Min Act: -0.1700
Data Index: 2555888 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.0561. Min Act: -0.1700
Data Index: 4775772 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.0874. Min Act: -0.1700
Data Index: 7661064 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.0561. Min Act: -0.1700
Data Index: 8751317 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.0561. Min Act: -0.1700
Data Index: 8190480 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.0561. Min Act: -0.1700
Data Index: 192319 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.0561. Min Act: -0.1700
Data Index: 897968 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5874. Min Range: -5.5874
Max Act: 4.9936. Min Act: -0.1700
Data Index: 3629110 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5874. Min Range: -5.5874
Max Act: 5.0249. Min Act: -0.1700
Data Index: 1787549 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5874. Min Range: -5.5874
Max Act: 4.9936. Min Act: -0.1700
Data Index: 4255015 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5874. Min Range: -5.5874
Max Act: 4.9936. Min Act: -0.1700
Data Index: 2505328 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5874. Min Range: -5.5874
Max Act: 4.9936. Min Act: -0.1700
Data Index: 455905 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5874. Min Range: -5.5874
Max Act: 4.9936. Min Act: -0.1700
Data Index: 2765341 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19