Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1686 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3355. Min Range: -8.3355
Max Act: 8.3355. Min Act: -0.1700
Data Index: 135578 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.8980. Min Act: -0.1700
Data Index: 6755057 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.7730. Min Act: -0.1700
Data Index: 7148006 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.7105. Min Act: -0.1700
Data Index: 407711 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.5855. Min Act: -0.1700
Data Index: 1996193 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.4918. Min Act: -0.1700
Data Index: 5103325 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.4918. Min Act: -0.1700
Data Index: 8780762 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.4293. Min Act: -0.1700
Data Index: 5456562 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.3980. Min Act: -0.1700
Data Index: 1147667 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.3668. Min Act: -0.1700
Data Index: 1068025 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.3355. Min Act: -0.1700
Data Index: 1584489 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.3668. Min Act: -0.1700
Data Index: 8168909 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.3355. Min Act: -0.1700
Data Index: 2638668 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.3355. Min Act: -0.1700
Data Index: 6018600 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.3355. Min Act: -0.1700
Data Index: 2264203 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.3043. Min Act: -0.1700
Data Index: 328800 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.2418. Min Act: -0.1700
Data Index: 6490285 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.2730. Min Act: -0.1700
Data Index: 7871930 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.2730. Min Act: -0.1700
Data Index: 7932290 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3355. Min Range: -8.3355
Max Act: 7.2418. Min Act: -0.1700
Data Index: 8521856 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19