Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4995 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.5967. Min Act: -0.1700
Data Index: 262040 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.4717. Min Act: -0.1700
Data Index: 5792598 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.3467. Min Act: -0.1700
Data Index: 1162501 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.2217. Min Act: -0.1700
Data Index: 5630577 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.2530. Min Act: -0.1700
Data Index: 7743765 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0967. Min Act: -0.1700
Data Index: 6420456 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0967. Min Act: -0.1700
Data Index: 2115468 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0967. Min Act: -0.1700
Data Index: 7463990 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0967. Min Act: -0.1700
Data Index: 7273130 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0655. Min Act: -0.1700
Data Index: 6801240 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0655. Min Act: -0.1700
Data Index: 7001502 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0030. Min Act: -0.1700
Data Index: 242254 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0342. Min Act: -0.1700
Data Index: 5707758 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0342. Min Act: -0.1700
Data Index: 8418075 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0342. Min Act: -0.1700
Data Index: 3602597 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0030. Min Act: -0.1700
Data Index: 5671632 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5967. Min Range: -6.5967
Max Act: 6.0030. Min Act: -0.1700
Data Index: 1951693 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5967. Min Range: -6.5967
Max Act: 5.9092. Min Act: -0.1700
Data Index: 3591458 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5967. Min Range: -6.5967
Max Act: 5.9405. Min Act: -0.1700
Data Index: 4098343 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5967. Min Range: -6.5967
Max Act: 5.9405. Min Act: -0.1700
Data Index: 3828936 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19