Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1215 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.5013. Min Act: -0.1700
Data Index: 5232113 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.4701. Min Act: -0.1700
Data Index: 5232114 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.4388. Min Act: -0.1700
Data Index: 2282607 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.3451. Min Act: -0.1700
Data Index: 219233 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.2826. Min Act: -0.1700
Data Index: 1950930 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.2826. Min Act: -0.1700
Data Index: 5641103 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.2201. Min Act: -0.1700
Data Index: 1854214 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.2513. Min Act: -0.1700
Data Index: 2153970 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.2201. Min Act: -0.1700
Data Index: 4573888 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.2513. Min Act: -0.1700
Data Index: 6544634 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.2201. Min Act: -0.1700
Data Index: 230015 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.1576. Min Act: -0.1700
Data Index: 2042049 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.1888. Min Act: -0.1700
Data Index: 5075582 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.1576. Min Act: -0.1700
Data Index: 1592335 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.1576. Min Act: -0.1700
Data Index: 3831783 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.1263. Min Act: -0.1700
Data Index: 116322 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.1263. Min Act: -0.1700
Data Index: 1565162 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.1263. Min Act: -0.1700
Data Index: 5601865 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.0950. Min Act: -0.1700
Data Index: 6141799 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5013. Min Range: -4.5013
Max Act: 4.1263. Min Act: -0.1700
Data Index: 7387654 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19