Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4784. Min Range: -6.4784
Max Act: 6.4784. Min Act: -0.1700
Data Index: 2007746 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4784. Min Range: -6.4784
Max Act: 6.3221. Min Act: -0.1700
Data Index: 7206572 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4784. Min Range: -6.4784
Max Act: 6.1034. Min Act: -0.1700
Data Index: 3864335 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4784. Min Range: -6.4784
Max Act: 6.0409. Min Act: -0.1700
Data Index: 1902217 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4784. Min Range: -6.4784
Max Act: 6.0721. Min Act: -0.1700
Data Index: 2915808 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.9471. Min Act: -0.1700
Data Index: 780279 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.9159. Min Act: -0.1700
Data Index: 8038195 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.9159. Min Act: -0.1700
Data Index: 3846700 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.8846. Min Act: -0.1700
Data Index: 4809661 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.9159. Min Act: -0.1700
Data Index: 2753895 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.8846. Min Act: -0.1700
Data Index: 2493822 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.8534. Min Act: -0.1700
Data Index: 780278 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.8534. Min Act: -0.1700
Data Index: 2714328 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.8534. Min Act: -0.1700
Data Index: 2722008 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.8221. Min Act: -0.1700
Data Index: 189386 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.8221. Min Act: -0.1700
Data Index: 417211 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.8221. Min Act: -0.1700
Data Index: 6263169 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.7909. Min Act: -0.1700
Data Index: 3963036 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.7909. Min Act: -0.1700
Data Index: 5885581 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4784. Min Range: -6.4784
Max Act: 5.7909. Min Act: -0.1700
Data Index: 2870484 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19