Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1170. Min Range: -8.1170
Max Act: 8.1170. Min Act: -0.1700
Data Index: 124379 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1170. Min Range: -8.1170
Max Act: 8.1170. Min Act: -0.1700
Data Index: 8107990 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1170. Min Range: -8.1170
Max Act: 8.1170. Min Act: -0.1700
Data Index: 7423527 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1170. Min Range: -8.1170
Max Act: 8.0545. Min Act: -0.1700
Data Index: 4968095 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1170. Min Range: -8.1170
Max Act: 8.0545. Min Act: -0.1700
Data Index: 6861998 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.9920. Min Act: -0.1700
Data Index: 6313179 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.9295. Min Act: -0.1700
Data Index: 2616280 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.9295. Min Act: -0.1700
Data Index: 3286556 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.9295. Min Act: -0.1700
Data Index: 6861996 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.8670. Min Act: -0.1700
Data Index: 586827 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.8670. Min Act: -0.1700
Data Index: 82369 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.8670. Min Act: -0.1700
Data Index: 6901529 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.8357. Min Act: -0.1700
Data Index: 4304041 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.7732. Min Act: -0.1700
Data Index: 7943791 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.7420. Min Act: -0.1700
Data Index: 5872028 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.7420. Min Act: -0.1700
Data Index: 7816833 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.7732. Min Act: -0.1700
Data Index: 140495 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.7420. Min Act: -0.1700
Data Index: 466631 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.7420. Min Act: -0.1700
Data Index: 8814062 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1170. Min Range: -8.1170
Max Act: 7.7107. Min Act: -0.1700
Data Index: 7103776 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19