Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6075. Min Range: -6.6075
Max Act: 6.6075. Min Act: -0.1700
Data Index: 6142179 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6075. Min Range: -6.6075
Max Act: 6.1388. Min Act: -0.1700
Data Index: 7295599 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.9825. Min Act: -0.1700
Data Index: 2250563 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.8888. Min Act: -0.1700
Data Index: 30011 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.9200. Min Act: -0.1700
Data Index: 2498668 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.7950. Min Act: -0.1700
Data Index: 6568444 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.7638. Min Act: -0.1700
Data Index: 6883739 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.7950. Min Act: -0.1700
Data Index: 568097 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.7638. Min Act: -0.1700
Data Index: 973679 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.7325. Min Act: -0.1700
Data Index: 564515 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.7325. Min Act: -0.1700
Data Index: 844515 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.7325. Min Act: -0.1700
Data Index: 5130568 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.7013. Min Act: -0.1700
Data Index: 6313635 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.7013. Min Act: -0.1700
Data Index: 2365221 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.6700. Min Act: -0.1700
Data Index: 1563353 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.6700. Min Act: -0.1700
Data Index: 3399023 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.6075. Min Act: -0.1700
Data Index: 1785970 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.6075. Min Act: -0.1700
Data Index: 4106825 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.6388. Min Act: -0.1700
Data Index: 7801316 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6075. Min Range: -6.6075
Max Act: 5.6388. Min Act: -0.1700
Data Index: 6210670 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19