Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5890 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.7491. Min Act: -0.1700
Data Index: 7773128 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.6554. Min Act: -0.1700
Data Index: 5609299 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.4366. Min Act: -0.1700
Data Index: 6696604 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.3429. Min Act: -0.1700
Data Index: 7185662 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.3116. Min Act: -0.1700
Data Index: 1993844 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.3116. Min Act: -0.1700
Data Index: 3555092 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.2804. Min Act: -0.1700
Data Index: 6102510 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.2491. Min Act: -0.1700
Data Index: 7518897 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.2491. Min Act: -0.1700
Data Index: 5765907 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.2179. Min Act: -0.1700
Data Index: 7966124 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.1866. Min Act: -0.1700
Data Index: 8701259 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.1866. Min Act: -0.1700
Data Index: 6903953 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.1241. Min Act: -0.1700
Data Index: 2451315 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.1241. Min Act: -0.1700
Data Index: 32012 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.1241. Min Act: -0.1700
Data Index: 8441296 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.1241. Min Act: -0.1700
Data Index: 3763467 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.0929. Min Act: -0.1700
Data Index: 6147710 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.0929. Min Act: -0.1700
Data Index: 5505373 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.0616. Min Act: -0.1700
Data Index: 3817696 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7491. Min Range: -6.7491
Max Act: 6.0616. Min Act: -0.1700
Data Index: 3473387 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19