Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 19.6248. Min Range: -19.6248
Max Act: 19.6248. Min Act: -0.1700
Data Index: 6370721 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.6248. Min Range: -19.6248
Max Act: 19.3748. Min Act: -0.1700
Data Index: 2029075 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.6248. Min Range: -19.6248
Max Act: 19.3748. Min Act: -0.1700
Data Index: 8148656 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.6248. Min Range: -19.6248
Max Act: 19.1248. Min Act: -0.1700
Data Index: 6573481 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.6248. Min Range: -19.6248
Max Act: 19.2498. Min Act: -0.1700
Data Index: 7961518 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.6248. Min Range: -19.6248
Max Act: 19.1248. Min Act: -0.1700
Data Index: 6663163 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.6248. Min Range: -19.6248
Max Act: 19.1248. Min Act: -0.1700
Data Index: 3608674 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.6248. Min Range: -19.6248
Max Act: 19.1248. Min Act: -0.1700
Data Index: 5713803 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.9998. Min Act: -0.1700
Data Index: 6573485 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.9998. Min Act: -0.1700
Data Index: 1539726 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.9998. Min Act: -0.1700
Data Index: 4677381 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.9998. Min Act: -0.1700
Data Index: 4473920 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.9998. Min Act: -0.1700
Data Index: 2574 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.9998. Min Act: -0.1700
Data Index: 4945904 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.8748. Min Act: -0.1700
Data Index: 5547488 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.8748. Min Act: -0.1700
Data Index: 8079205 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.8748. Min Act: -0.1700
Data Index: 5511310 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.8748. Min Act: -0.1700
Data Index: 6573487 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.7498. Min Act: -0.1700
Data Index: 5245962 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.6248. Min Range: -19.6248
Max Act: 18.7498. Min Act: -0.1700
Data Index: 7545653 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19