Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.9094. Min Act: -0.1700
Data Index: 7253089 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.6281. Min Act: -0.1700
Data Index: 5213708 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.5969. Min Act: -0.1700
Data Index: 5294236 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.5969. Min Act: -0.1700
Data Index: 6777503 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.5969. Min Act: -0.1700
Data Index: 3223836 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.5969. Min Act: -0.1700
Data Index: 2282360 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.5656. Min Act: -0.1700
Data Index: 2699463 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.5344. Min Act: -0.1700
Data Index: 7164623 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.5344. Min Act: -0.1700
Data Index: 988591 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.5344. Min Act: -0.1700
Data Index: 489503 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.4719. Min Act: -0.1700
Data Index: 1285735 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.4719. Min Act: -0.1700
Data Index: 5533069 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.4719. Min Act: -0.1700
Data Index: 920487 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.5031. Min Act: -0.1700
Data Index: 2763355 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.4719. Min Act: -0.1700
Data Index: 4753876 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.4406. Min Act: -0.1700
Data Index: 1732797 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.4094. Min Act: -0.1700
Data Index: 4326956 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.4094. Min Act: -0.1700
Data Index: 3098441 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.3781. Min Act: -0.1700
Data Index: 406484 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9094. Min Range: -5.9094
Max Act: 5.3469. Min Act: -0.1700
Data Index: 6070287 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19