Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5077 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3673. Min Range: -6.3673
Max Act: 6.3673. Min Act: -0.1700
Data Index: 6166268 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3673. Min Range: -6.3673
Max Act: 6.1798. Min Act: -0.1700
Data Index: 5503424 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3673. Min Range: -6.3673
Max Act: 6.1485. Min Act: -0.1700
Data Index: 8450311 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3673. Min Range: -6.3673
Max Act: 6.1173. Min Act: -0.1700
Data Index: 4165500 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.9610. Min Act: -0.1700
Data Index: 3072101 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.8985. Min Act: -0.1700
Data Index: 2619285 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.8360. Min Act: -0.1700
Data Index: 2251682 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.8360. Min Act: -0.1700
Data Index: 802172 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.8360. Min Act: -0.1700
Data Index: 5778832 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.8673. Min Act: -0.1700
Data Index: 6403179 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.8048. Min Act: -0.1700
Data Index: 1262353 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.7735. Min Act: -0.1700
Data Index: 7582683 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.8048. Min Act: -0.1700
Data Index: 2885363 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.8048. Min Act: -0.1700
Data Index: 6388780 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.7735. Min Act: -0.1700
Data Index: 7259845 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.7735. Min Act: -0.1700
Data Index: 770179 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.7735. Min Act: -0.1700
Data Index: 6526856 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.7110. Min Act: -0.1700
Data Index: 8417751 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.7735. Min Act: -0.1700
Data Index: 2528411 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3673. Min Range: -6.3673
Max Act: 5.7423. Min Act: -0.1700
Data Index: 768654 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19