Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5194 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2523. Min Range: -5.2523
Max Act: 5.2523. Min Act: -0.1700
Data Index: 4357035 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2523. Min Range: -5.2523
Max Act: 5.0023. Min Act: -0.1700
Data Index: 5143358 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.9711. Min Act: -0.1700
Data Index: 2041784 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.8773. Min Act: -0.1700
Data Index: 2542328 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.8461. Min Act: -0.1700
Data Index: 320282 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.8461. Min Act: -0.1700
Data Index: 4399952 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.8461. Min Act: -0.1700
Data Index: 2270701 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.8461. Min Act: -0.1700
Data Index: 2071354 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.8461. Min Act: -0.1700
Data Index: 391367 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.8461. Min Act: -0.1700
Data Index: 519698 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.8773. Min Act: -0.1700
Data Index: 7973219 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.8148. Min Act: -0.1700
Data Index: 2658944 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.8148. Min Act: -0.1700
Data Index: 3123726 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.7836. Min Act: -0.1700
Data Index: 4357030 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.7836. Min Act: -0.1700
Data Index: 6135315 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.7523. Min Act: -0.1700
Data Index: 7822796 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.7523. Min Act: -0.1700
Data Index: 7292345 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.7523. Min Act: -0.1700
Data Index: 6681005 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.7523. Min Act: -0.1700
Data Index: 4098172 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2523. Min Range: -5.2523
Max Act: 4.7523. Min Act: -0.1700
Data Index: 4105999 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19