Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0120. Min Range: -8.0120
Max Act: 8.0120. Min Act: -0.1700
Data Index: 4548737 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.8870. Min Act: -0.1700
Data Index: 5621810 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.7620. Min Act: -0.1700
Data Index: 1098563 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.5745. Min Act: -0.1700
Data Index: 4484789 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.4807. Min Act: -0.1700
Data Index: 5500698 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.4495. Min Act: -0.1700
Data Index: 3883487 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.4182. Min Act: -0.1700
Data Index: 5509125 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.3557. Min Act: -0.1700
Data Index: 365153 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.3245. Min Act: -0.1700
Data Index: 8071667 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.3557. Min Act: -0.1700
Data Index: 1827454 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.3870. Min Act: -0.1700
Data Index: 8071668 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.3557. Min Act: -0.1700
Data Index: 7831008 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.3245. Min Act: -0.1700
Data Index: 7507270 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.3245. Min Act: -0.1700
Data Index: 1911006 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.2932. Min Act: -0.1700
Data Index: 5329173 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.2932. Min Act: -0.1700
Data Index: 6268194 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.2932. Min Act: -0.1700
Data Index: 6378443 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.2620. Min Act: -0.1700
Data Index: 3720493 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.2620. Min Act: -0.1700
Data Index: 53258 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0120. Min Range: -8.0120
Max Act: 7.2620. Min Act: -0.1700
Data Index: 6953144 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19