Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2225 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.5746. Min Act: -0.1700
Data Index: 3513942 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.4184. Min Act: -0.1700
Data Index: 5585695 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.3246. Min Act: -0.1700
Data Index: 1595258 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.3246. Min Act: -0.1700
Data Index: 8313590 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.2309. Min Act: -0.1700
Data Index: 5143437 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.2621. Min Act: -0.1700
Data Index: 3503996 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1996. Min Act: -0.1700
Data Index: 7968244 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1996. Min Act: -0.1700
Data Index: 4996581 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1996. Min Act: -0.1700
Data Index: 1081094 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1684. Min Act: -0.1700
Data Index: 8821840 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1684. Min Act: -0.1700
Data Index: 1919196 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1371. Min Act: -0.1700
Data Index: 1691101 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1371. Min Act: -0.1700
Data Index: 5259340 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1059. Min Act: -0.1700
Data Index: 3016250 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.0746. Min Act: -0.1700
Data Index: 3658285 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.1059. Min Act: -0.1700
Data Index: 3953185 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.0746. Min Act: -0.1700
Data Index: 1410311 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.0746. Min Act: -0.1700
Data Index: 3867062 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.0746. Min Act: -0.1700
Data Index: 8557919 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5746. Min Range: -5.5746
Max Act: 5.0746. Min Act: -0.1700
Data Index: 178610 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19