Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.4418. Min Act: -0.1700
Data Index: 5051088 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.3481. Min Act: -0.1700
Data Index: 892084 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.1918. Min Act: -0.1700
Data Index: 4181396 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.1606. Min Act: -0.1700
Data Index: 1971957 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.1293. Min Act: -0.1700
Data Index: 5506794 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.1293. Min Act: -0.1700
Data Index: 3952891 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.1293. Min Act: -0.1700
Data Index: 7694951 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.0981. Min Act: -0.1700
Data Index: 18291 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.1293. Min Act: -0.1700
Data Index: 2327770 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.1293. Min Act: -0.1700
Data Index: 8715394 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.1293. Min Act: -0.1700
Data Index: 5412610 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.1293. Min Act: -0.1700
Data Index: 3312882 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.0981. Min Act: -0.1700
Data Index: 4813984 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.0981. Min Act: -0.1700
Data Index: 103824 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.0981. Min Act: -0.1700
Data Index: 2103888 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.0981. Min Act: -0.1700
Data Index: 6018627 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.0668. Min Act: -0.1700
Data Index: 2424624 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.0668. Min Act: -0.1700
Data Index: 6692525 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.0668. Min Act: -0.1700
Data Index: 4009667 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4418. Min Range: -5.4418
Max Act: 5.0668. Min Act: -0.1700
Data Index: 243227 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19