Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2938 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4103. Min Range: -8.4103
Max Act: 8.4103. Min Act: -0.1700
Data Index: 7467690 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4103. Min Range: -8.4103
Max Act: 8.1603. Min Act: -0.1700
Data Index: 2406048 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4103. Min Range: -8.4103
Max Act: 8.0353. Min Act: -0.1700
Data Index: 2406049 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4103. Min Range: -8.4103
Max Act: 8.0353. Min Act: -0.1700
Data Index: 4813659 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.9415. Min Act: -0.1700
Data Index: 2406058 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.9415. Min Act: -0.1700
Data Index: 2690726 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.9103. Min Act: -0.1700
Data Index: 708948 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.8478. Min Act: -0.1700
Data Index: 498421 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.8790. Min Act: -0.1700
Data Index: 6504794 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.8165. Min Act: -0.1700
Data Index: 5263607 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.7540. Min Act: -0.1700
Data Index: 8037528 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.7540. Min Act: -0.1700
Data Index: 899800 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.7228. Min Act: -0.1700
Data Index: 7817927 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.6915. Min Act: -0.1700
Data Index: 4111256 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.6915. Min Act: -0.1700
Data Index: 1883840 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.6915. Min Act: -0.1700
Data Index: 1567738 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.6915. Min Act: -0.1700
Data Index: 1587833 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.6603. Min Act: -0.1700
Data Index: 3657121 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.6290. Min Act: -0.1700
Data Index: 4489436 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4103. Min Range: -8.4103
Max Act: 7.5978. Min Act: -0.1700
Data Index: 6964236 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19