Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 187 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0290. Min Range: -7.0290
Max Act: 7.0290. Min Act: -0.1700
Data Index: 4972324 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.7790. Min Act: -0.1700
Data Index: 7732014 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.7478. Min Act: -0.1700
Data Index: 6032958 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.7165. Min Act: -0.1700
Data Index: 2264100 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.6228. Min Act: -0.1700
Data Index: 6550047 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.6228. Min Act: -0.1700
Data Index: 2591044 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.6228. Min Act: -0.1700
Data Index: 5958663 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5915. Min Act: -0.1700
Data Index: 5671028 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.6228. Min Act: -0.1700
Data Index: 4926120 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5915. Min Act: -0.1700
Data Index: 4422209 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5915. Min Act: -0.1700
Data Index: 7214956 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5915. Min Act: -0.1700
Data Index: 6445934 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5603. Min Act: -0.1700
Data Index: 8138650 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5603. Min Act: -0.1700
Data Index: 2021455 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5290. Min Act: -0.1700
Data Index: 2588714 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5603. Min Act: -0.1700
Data Index: 2829390 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5603. Min Act: -0.1700
Data Index: 2302671 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5603. Min Act: -0.1700
Data Index: 8567383 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5915. Min Act: -0.1700
Data Index: 262945 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0290. Min Range: -7.0290
Max Act: 6.5290. Min Act: -0.1700
Data Index: 1740264 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19