Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1801 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3980. Min Range: -7.3980
Max Act: 7.3980. Min Act: -0.1700
Data Index: 1497879 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3980. Min Range: -7.3980
Max Act: 7.3042. Min Act: -0.1700
Data Index: 1520248 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3980. Min Range: -7.3980
Max Act: 7.1167. Min Act: -0.1700
Data Index: 511844 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3980. Min Range: -7.3980
Max Act: 7.0542. Min Act: -0.1700
Data Index: 3974401 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3980. Min Range: -7.3980
Max Act: 7.0542. Min Act: -0.1700
Data Index: 5000846 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3980. Min Range: -7.3980
Max Act: 7.0230. Min Act: -0.1700
Data Index: 3468914 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.9292. Min Act: -0.1700
Data Index: 804281 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.8980. Min Act: -0.1700
Data Index: 6217126 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.8667. Min Act: -0.1700
Data Index: 182365 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.8355. Min Act: -0.1700
Data Index: 7322239 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.8355. Min Act: -0.1700
Data Index: 3118780 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.8355. Min Act: -0.1700
Data Index: 3121215 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.8355. Min Act: -0.1700
Data Index: 8806735 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.8355. Min Act: -0.1700
Data Index: 7024884 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.8042. Min Act: -0.1700
Data Index: 1163876 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.7417. Min Act: -0.1700
Data Index: 4161059 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.7730. Min Act: -0.1700
Data Index: 8806736 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.7417. Min Act: -0.1700
Data Index: 509501 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.7417. Min Act: -0.1700
Data Index: 4262997 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3980. Min Range: -7.3980
Max Act: 6.7417. Min Act: -0.1700
Data Index: 3155707 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19