Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2752 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.4422. Min Act: -0.1700
Data Index: 5047514 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.3172. Min Act: -0.1700
Data Index: 1588648 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.2860. Min Act: -0.1700
Data Index: 8562638 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.2860. Min Act: -0.1700
Data Index: 6621759 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.1922. Min Act: -0.1700
Data Index: 7037911 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.1610. Min Act: -0.1700
Data Index: 340983 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.0985. Min Act: -0.1700
Data Index: 8010329 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.1922. Min Act: -0.1700
Data Index: 6578810 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.1297. Min Act: -0.1700
Data Index: 6014802 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.1297. Min Act: -0.1700
Data Index: 6366811 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.0985. Min Act: -0.1700
Data Index: 4555074 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.0360. Min Act: -0.1700
Data Index: 2324479 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.0360. Min Act: -0.1700
Data Index: 4136501 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.0047. Min Act: -0.1700
Data Index: 2732957 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.0360. Min Act: -0.1700
Data Index: 4037282 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.0047. Min Act: -0.1700
Data Index: 6955677 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4422. Min Range: -5.4422
Max Act: 4.9735. Min Act: -0.1700
Data Index: 6437118 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.0360. Min Act: -0.1700
Data Index: 5107011 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4422. Min Range: -5.4422
Max Act: 4.9735. Min Act: -0.1700
Data Index: 4347678 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4422. Min Range: -5.4422
Max Act: 5.0047. Min Act: -0.1700
Data Index: 5394002 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19