Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2597 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4391. Min Range: -9.4391
Max Act: 9.4391. Min Act: -0.1700
Data Index: 8015149 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.3766. Min Act: -0.1700
Data Index: 213342 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.3766. Min Act: -0.1700
Data Index: 1351312 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.2516. Min Act: -0.1700
Data Index: 2987396 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.1891. Min Act: -0.1700
Data Index: 7878752 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.1266. Min Act: -0.1700
Data Index: 3391926 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.0016. Min Act: -0.1700
Data Index: 3955000 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.0641. Min Act: -0.1700
Data Index: 2050727 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.0641. Min Act: -0.1700
Data Index: 2793596 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.0016. Min Act: -0.1700
Data Index: 6749699 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.0641. Min Act: -0.1700
Data Index: 1322776 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.0016. Min Act: -0.1700
Data Index: 8625844 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.0016. Min Act: -0.1700
Data Index: 6247422 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4391. Min Range: -9.4391
Max Act: 8.0016. Min Act: -0.1700
Data Index: 3017908 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4391. Min Range: -9.4391
Max Act: 7.8766. Min Act: -0.1700
Data Index: 2279162 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4391. Min Range: -9.4391
Max Act: 7.9391. Min Act: -0.1700
Data Index: 1318345 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4391. Min Range: -9.4391
Max Act: 7.8766. Min Act: -0.1700
Data Index: 4670395 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4391. Min Range: -9.4391
Max Act: 7.8766. Min Act: -0.1700
Data Index: 7868975 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4391. Min Range: -9.4391
Max Act: 7.8141. Min Act: -0.1700
Data Index: 1510274 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4391. Min Range: -9.4391
Max Act: 7.8141. Min Act: -0.1700
Data Index: 563055 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19