Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.5449. Min Act: -0.1700
Data Index: 5466672 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.4199. Min Act: -0.1700
Data Index: 4453390 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.3886. Min Act: -0.1700
Data Index: 5555036 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.3886. Min Act: -0.1700
Data Index: 736813 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.2949. Min Act: -0.1700
Data Index: 2802587 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.3261. Min Act: -0.1700
Data Index: 5437450 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.2636. Min Act: -0.1700
Data Index: 3743098 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.2011. Min Act: -0.1700
Data Index: 2451348 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.2324. Min Act: -0.1700
Data Index: 104341 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.2324. Min Act: -0.1700
Data Index: 81189 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.2636. Min Act: -0.1700
Data Index: 5789373 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.2011. Min Act: -0.1700
Data Index: 7707754 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.1699. Min Act: -0.1700
Data Index: 1688263 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.1699. Min Act: -0.1700
Data Index: 7988125 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.1699. Min Act: -0.1700
Data Index: 7405415 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.1699. Min Act: -0.1700
Data Index: 2611085 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.1699. Min Act: -0.1700
Data Index: 5141796 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.1699. Min Act: -0.1700
Data Index: 210802 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.1386. Min Act: -0.1700
Data Index: 3054523 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5449. Min Range: -5.5449
Max Act: 5.1386. Min Act: -0.1700
Data Index: 3619320 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19