Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5372 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2524. Min Range: -5.2524
Max Act: 5.2524. Min Act: -0.1700
Data Index: 3631179 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2524. Min Range: -5.2524
Max Act: 5.0649. Min Act: -0.1700
Data Index: 8364461 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2524. Min Range: -5.2524
Max Act: 5.0337. Min Act: -0.1700
Data Index: 2100606 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.9399. Min Act: -0.1700
Data Index: 3348820 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.9087. Min Act: -0.1700
Data Index: 7593476 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.8462. Min Act: -0.1700
Data Index: 4104145 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.8462. Min Act: -0.1700
Data Index: 716013 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.8462. Min Act: -0.1700
Data Index: 2951410 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.8462. Min Act: -0.1700
Data Index: 8513308 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.7837. Min Act: -0.1700
Data Index: 4653961 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.7524. Min Act: -0.1700
Data Index: 8111086 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.7524. Min Act: -0.1700
Data Index: 62302 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.7524. Min Act: -0.1700
Data Index: 3108055 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.7212. Min Act: -0.1700
Data Index: 5432020 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.7212. Min Act: -0.1700
Data Index: 4401049 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.7212. Min Act: -0.1700
Data Index: 6574826 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.6899. Min Act: -0.1700
Data Index: 3606072 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.6899. Min Act: -0.1700
Data Index: 6478642 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.6899. Min Act: -0.1700
Data Index: 1600622 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2524. Min Range: -5.2524
Max Act: 4.6899. Min Act: -0.1700
Data Index: 3672929 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19