Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 218 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1649. Min Range: -5.1649
Max Act: 5.1649. Min Act: -0.1700
Data Index: 3691778 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1649. Min Range: -5.1649
Max Act: 5.1649. Min Act: -0.1700
Data Index: 3691775 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1649. Min Range: -5.1649
Max Act: 5.1024. Min Act: -0.1700
Data Index: 7271400 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1649. Min Range: -5.1649
Max Act: 5.0712. Min Act: -0.1700
Data Index: 4713980 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1649. Min Range: -5.1649
Max Act: 5.1024. Min Act: -0.1700
Data Index: 1904651 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1649. Min Range: -5.1649
Max Act: 5.1024. Min Act: -0.1700
Data Index: 3120402 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1649. Min Range: -5.1649
Max Act: 5.0712. Min Act: -0.1700
Data Index: 8499523 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1649. Min Range: -5.1649
Max Act: 5.0087. Min Act: -0.1700
Data Index: 7271391 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1649. Min Range: -5.1649
Max Act: 5.0087. Min Act: -0.1700
Data Index: 89528 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.9774. Min Act: -0.1700
Data Index: 6992888 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.9462. Min Act: -0.1700
Data Index: 8574708 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.9462. Min Act: -0.1700
Data Index: 924860 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.9774. Min Act: -0.1700
Data Index: 1611253 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.9462. Min Act: -0.1700
Data Index: 4204141 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.9149. Min Act: -0.1700
Data Index: 984736 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.9149. Min Act: -0.1700
Data Index: 3859937 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.8837. Min Act: -0.1700
Data Index: 8113785 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.8837. Min Act: -0.1700
Data Index: 4385995 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.8837. Min Act: -0.1700
Data Index: 1677250 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1649. Min Range: -5.1649
Max Act: 4.8837. Min Act: -0.1700
Data Index: 312488 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19