Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 880 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.9403. Min Act: -0.1700
Data Index: 5810482 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.6903. Min Act: -0.1700
Data Index: 4147483 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.7215. Min Act: -0.1700
Data Index: 7804716 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.7215. Min Act: -0.1700
Data Index: 4279567 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.6590. Min Act: -0.1700
Data Index: 4202457 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.6903. Min Act: -0.1700
Data Index: 2978960 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5653. Min Act: -0.1700
Data Index: 2205624 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5965. Min Act: -0.1700
Data Index: 4584461 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5340. Min Act: -0.1700
Data Index: 891507 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5340. Min Act: -0.1700
Data Index: 8802970 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5340. Min Act: -0.1700
Data Index: 2789159 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5340. Min Act: -0.1700
Data Index: 6617759 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5340. Min Act: -0.1700
Data Index: 2777623 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5340. Min Act: -0.1700
Data Index: 4470633 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.5028. Min Act: -0.1700
Data Index: 89563 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.4715. Min Act: -0.1700
Data Index: 7312169 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.4715. Min Act: -0.1700
Data Index: 5538786 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.4403. Min Act: -0.1700
Data Index: 198753 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.4090. Min Act: -0.1700
Data Index: 6650210 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9403. Min Range: -6.9403
Max Act: 6.4090. Min Act: -0.1700
Data Index: 3880350 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19