Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.8594. Min Act: -0.1700
Data Index: 3037908 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.8594. Min Act: -0.1700
Data Index: 8149146 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.8594. Min Act: -0.1700
Data Index: 7326941 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.7656. Min Act: -0.1700
Data Index: 3644375 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.7031. Min Act: -0.1700
Data Index: 6483772 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.7031. Min Act: -0.1700
Data Index: 2875406 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.6406. Min Act: -0.1700
Data Index: 2274756 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.6406. Min Act: -0.1700
Data Index: 1855267 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.6406. Min Act: -0.1700
Data Index: 2969419 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.6094. Min Act: -0.1700
Data Index: 4450239 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.6094. Min Act: -0.1700
Data Index: 2935867 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.6094. Min Act: -0.1700
Data Index: 5830206 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.5469. Min Act: -0.1700
Data Index: 496894 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.5156. Min Act: -0.1700
Data Index: 7092690 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.5469. Min Act: -0.1700
Data Index: 70553 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.5156. Min Act: -0.1700
Data Index: 8587164 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.5469. Min Act: -0.1700
Data Index: 5386967 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.4844. Min Act: -0.1700
Data Index: 6203880 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.4844. Min Act: -0.1700
Data Index: 6964433 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8594. Min Range: -5.8594
Max Act: 5.4844. Min Act: -0.1700
Data Index: 4306510 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19