Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1158 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0538. Min Range: -4.0538
Max Act: 4.0538. Min Act: -0.1700
Data Index: 8420445 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0538. Min Range: -4.0538
Max Act: 4.0226. Min Act: -0.1700
Data Index: 1461394 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.9601. Min Act: -0.1700
Data Index: 3651335 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.9132. Min Act: -0.1700
Data Index: 3770894 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.9288. Min Act: -0.1700
Data Index: 7485672 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.9132. Min Act: -0.1700
Data Index: 40432 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.9288. Min Act: -0.1700
Data Index: 3466077 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.9288. Min Act: -0.1700
Data Index: 255634 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.9444. Min Act: -0.1700
Data Index: 793991 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8663. Min Act: -0.1700
Data Index: 8567833 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8975. Min Act: -0.1700
Data Index: 7535458 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8506. Min Act: -0.1700
Data Index: 5749054 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8663. Min Act: -0.1700
Data Index: 7548137 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8506. Min Act: -0.1700
Data Index: 2981910 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8663. Min Act: -0.1700
Data Index: 8509745 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8506. Min Act: -0.1700
Data Index: 5343397 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8663. Min Act: -0.1700
Data Index: 456864 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8194. Min Act: -0.1700
Data Index: 8311573 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8506. Min Act: -0.1700
Data Index: 8648808 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0538. Min Range: -4.0538
Max Act: 3.8663. Min Act: -0.1700
Data Index: 6805065 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19