Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2458 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3173. Min Range: -5.3173
Max Act: 5.3173. Min Act: -0.1700
Data Index: 7805951 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3173. Min Range: -5.3173
Max Act: 5.0673. Min Act: -0.1700
Data Index: 7805978 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.9423. Min Act: -0.1700
Data Index: 6163162 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.9110. Min Act: -0.1700
Data Index: 4201694 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.8798. Min Act: -0.1700
Data Index: 6096919 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.8485. Min Act: -0.1700
Data Index: 318576 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.8798. Min Act: -0.1700
Data Index: 6193656 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.8173. Min Act: -0.1700
Data Index: 1956362 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.8173. Min Act: -0.1700
Data Index: 8058667 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.7860. Min Act: -0.1700
Data Index: 4017629 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.7860. Min Act: -0.1700
Data Index: 745350 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.7860. Min Act: -0.1700
Data Index: 7560550 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.7548. Min Act: -0.1700
Data Index: 765690 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.7548. Min Act: -0.1700
Data Index: 7540767 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.7548. Min Act: -0.1700
Data Index: 5276209 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.7235. Min Act: -0.1700
Data Index: 5966059 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.7235. Min Act: -0.1700
Data Index: 597143 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.7235. Min Act: -0.1700
Data Index: 1420601 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.6923. Min Act: -0.1700
Data Index: 6697773 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3173. Min Range: -5.3173
Max Act: 4.7235. Min Act: -0.1700
Data Index: 2310652 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19