Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5733 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1418. Min Range: -8.1418
Max Act: 8.1418. Min Act: -0.1700
Data Index: 2620925 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.8918. Min Act: -0.1700
Data Index: 3070827 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.8293. Min Act: -0.1700
Data Index: 1514328 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.8293. Min Act: -0.1700
Data Index: 1254346 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.7668. Min Act: -0.1700
Data Index: 713848 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.7668. Min Act: -0.1700
Data Index: 6972177 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.7043. Min Act: -0.1700
Data Index: 1913953 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.7043. Min Act: -0.1700
Data Index: 645244 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.6418. Min Act: -0.1700
Data Index: 5786538 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.6418. Min Act: -0.1700
Data Index: 3623030 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.5793. Min Act: -0.1700
Data Index: 230655 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.5793. Min Act: -0.1700
Data Index: 802697 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.5168. Min Act: -0.1700
Data Index: 8435306 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.4855. Min Act: -0.1700
Data Index: 2566513 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.4855. Min Act: -0.1700
Data Index: 8284421 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.4855. Min Act: -0.1700
Data Index: 1373725 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.4230. Min Act: -0.1700
Data Index: 5196642 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.4855. Min Act: -0.1700
Data Index: 7147826 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.4230. Min Act: -0.1700
Data Index: 1421926 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1418. Min Range: -8.1418
Max Act: 7.4230. Min Act: -0.1700
Data Index: 7574977 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19