Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2450 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.2342. Min Act: -0.1700
Data Index: 3118412 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.2028. Min Act: -0.1700
Data Index: 2307421 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.1083. Min Act: -0.1700
Data Index: 6085785 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.1083. Min Act: -0.1700
Data Index: 2838265 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.1083. Min Act: -0.1700
Data Index: 1321146 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.0768. Min Act: -0.1700
Data Index: 8208845 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.0926. Min Act: -0.1700
Data Index: 7531606 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.0452. Min Act: -0.1700
Data Index: 3468639 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.0452. Min Act: -0.1700
Data Index: 4897337 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.0295. Min Act: -0.1700
Data Index: 803465 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.0295. Min Act: -0.1699
Data Index: 4940372 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.0137. Min Act: -0.1127
Data Index: 2151830 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2342. Min Range: -3.2342
Max Act: 3.0295. Min Act: -0.1700
Data Index: 6292692 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2342. Min Range: -3.2342
Max Act: 2.9979. Min Act: -0.1700
Data Index: 6508964 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2342. Min Range: -3.2342
Max Act: 2.9979. Min Act: -0.1700
Data Index: 5915288 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2342. Min Range: -3.2342
Max Act: 2.9979. Min Act: -0.1700
Data Index: 4414909 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2342. Min Range: -3.2342
Max Act: 2.9821. Min Act: -0.1700
Data Index: 2277495 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2342. Min Range: -3.2342
Max Act: 2.9821. Min Act: -0.1700
Data Index: 8047471 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2342. Min Range: -3.2342
Max Act: 2.9662. Min Act: -0.1664
Data Index: 4855386 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2342. Min Range: -3.2342
Max Act: 2.9504. Min Act: -0.1700
Data Index: 6566621 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19