Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5163 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.6204. Min Act: -0.1700
Data Index: 6005875 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.5266. Min Act: -0.1700
Data Index: 4673678 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.5266. Min Act: -0.1700
Data Index: 8693241 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.4641. Min Act: -0.1700
Data Index: 3171217 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.4329. Min Act: -0.1700
Data Index: 3471879 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.4329. Min Act: -0.1700
Data Index: 7806357 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.4329. Min Act: -0.1700
Data Index: 2833007 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.4329. Min Act: -0.1700
Data Index: 4446715 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.4016. Min Act: -0.1700
Data Index: 4622187 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.3391. Min Act: -0.1700
Data Index: 4038865 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.3391. Min Act: -0.1700
Data Index: 7425164 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.2766. Min Act: -0.1700
Data Index: 1368654 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.2766. Min Act: -0.1700
Data Index: 1871138 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.3079. Min Act: -0.1700
Data Index: 346415 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.2766. Min Act: -0.1700
Data Index: 2563185 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.2766. Min Act: -0.1700
Data Index: 665240 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.2766. Min Act: -0.1700
Data Index: 8411851 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.2766. Min Act: -0.1700
Data Index: 6008572 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.2454. Min Act: -0.1700
Data Index: 8676362 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6204. Min Range: -6.6204
Max Act: 6.2454. Min Act: -0.1700
Data Index: 5546670 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19