Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.6063. Min Act: -0.1700
Data Index: 8012081 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.5750. Min Act: -0.1700
Data Index: 8195590 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.5750. Min Act: -0.1700
Data Index: 4400336 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.5437. Min Act: -0.1700
Data Index: 7730814 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.5437. Min Act: -0.1700
Data Index: 3847776 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.5437. Min Act: -0.1700
Data Index: 603613 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.5437. Min Act: -0.1700
Data Index: 8200203 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.5437. Min Act: -0.1700
Data Index: 4783819 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.5437. Min Act: -0.1700
Data Index: 4737588 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.5124. Min Act: -0.1700
Data Index: 5366191 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.5124. Min Act: -0.1700
Data Index: 4303020 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.4811. Min Act: -0.1700
Data Index: 1561594 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.4811. Min Act: -0.1700
Data Index: 2821662 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.4811. Min Act: -0.1700
Data Index: 7034722 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.4811. Min Act: -0.1700
Data Index: 2711122 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.4811. Min Act: -0.1700
Data Index: 8576654 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.4811. Min Act: -0.1700
Data Index: 5841343 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.4811. Min Act: -0.1700
Data Index: 1669433 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.4497. Min Act: -0.1700
Data Index: 3590265 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6063. Min Range: -3.6063
Max Act: 3.4497. Min Act: -0.1700
Data Index: 7221231 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19