Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0490. Min Range: -6.0490
Max Act: 6.0490. Min Act: -0.1700
Data Index: 235676 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.9553. Min Act: -0.1700
Data Index: 6000825 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.8615. Min Act: -0.1700
Data Index: 8710279 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.8303. Min Act: -0.1700
Data Index: 7549560 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7990. Min Act: -0.1698
Data Index: 7758054 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7990. Min Act: -0.1700
Data Index: 5940096 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7990. Min Act: -0.1699
Data Index: 8730345 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7990. Min Act: -0.1699
Data Index: 461855 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7678. Min Act: -0.1700
Data Index: 8462420 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7678. Min Act: -0.1700
Data Index: 2505547 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7678. Min Act: -0.1700
Data Index: 5545477 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7365. Min Act: -0.1699
Data Index: 7734055 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7365. Min Act: -0.1700
Data Index: 7672666 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7365. Min Act: -0.1700
Data Index: 1509459 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7365. Min Act: -0.1700
Data Index: 3713386 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7365. Min Act: -0.1700
Data Index: 3105744 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7365. Min Act: -0.1699
Data Index: 1507297 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7365. Min Act: -0.1700
Data Index: 642134 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7365. Min Act: -0.1698
Data Index: 7537696 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0490. Min Range: -6.0490
Max Act: 5.7365. Min Act: -0.1700
Data Index: 659472 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19