Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4492 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.9654. Min Act: -0.1700
Data Index: 240491 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.9341. Min Act: -0.1700
Data Index: 5535625 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.9029. Min Act: -0.1700
Data Index: 5501558 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.8716. Min Act: -0.1700
Data Index: 827021 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.8404. Min Act: -0.1700
Data Index: 6465530 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.8404. Min Act: -0.1700
Data Index: 5752749 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.8404. Min Act: -0.1700
Data Index: 2860098 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7779. Min Act: -0.1700
Data Index: 720921 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7779. Min Act: -0.1700
Data Index: 6666403 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7154. Min Act: -0.1700
Data Index: 591057 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7466. Min Act: -0.1700
Data Index: 5401555 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7466. Min Act: -0.1700
Data Index: 3026733 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7466. Min Act: -0.1700
Data Index: 8576751 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7154. Min Act: -0.1700
Data Index: 3091160 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7154. Min Act: -0.1700
Data Index: 4064686 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7154. Min Act: -0.1700
Data Index: 8078582 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7154. Min Act: -0.1700
Data Index: 203579 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7154. Min Act: -0.1700
Data Index: 6358934 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7154. Min Act: -0.1700
Data Index: 1374707 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9654. Min Range: -5.9654
Max Act: 5.7466. Min Act: -0.1700
Data Index: 3297572 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19