Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 643 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.5089. Min Act: -0.1700
Data Index: 5388929 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.5401. Min Act: -0.1700
Data Index: 8021953 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4776. Min Act: -0.1700
Data Index: 8126021 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4776. Min Act: -0.1700
Data Index: 1481367 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4464. Min Act: -0.1700
Data Index: 372797 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4776. Min Act: -0.1700
Data Index: 8279731 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3839. Min Act: -0.1700
Data Index: 6618573 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4151. Min Act: -0.1700
Data Index: 7968971 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4151. Min Act: -0.1700
Data Index: 6085515 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3526. Min Act: -0.1700
Data Index: 5705592 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3214. Min Act: -0.1700
Data Index: 508981 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3839. Min Act: -0.1700
Data Index: 7807686 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.2589. Min Act: -0.1700
Data Index: 7564087 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.2901. Min Act: -0.1700
Data Index: 5879066 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.2276. Min Act: -0.1700
Data Index: 3462835 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.2276. Min Act: -0.1700
Data Index: 2043116 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.2276. Min Act: -0.1700
Data Index: 6045734 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.1651. Min Act: -0.1700
Data Index: 3353842 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.1651. Min Act: -0.1700
Data Index: 5182932 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.1651. Min Act: -0.1700
Data Index: 2292302 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19