Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.9511. Min Act: -0.1700
Data Index: 1393331 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.8261. Min Act: -0.1700
Data Index: 1495721 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.7011. Min Act: -0.1700
Data Index: 8832412 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.6386. Min Act: -0.1700
Data Index: 6171795 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.6073. Min Act: -0.1700
Data Index: 4333044 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.5136. Min Act: -0.1700
Data Index: 6442517 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.4823. Min Act: -0.1700
Data Index: 2753692 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.5136. Min Act: -0.1699
Data Index: 7924807 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.4511. Min Act: -0.1700
Data Index: 6162275 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.4198. Min Act: -0.1700
Data Index: 7011367 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.3886. Min Act: -0.1700
Data Index: 2673343 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.4198. Min Act: -0.1700
Data Index: 6452680 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.3886. Min Act: -0.1700
Data Index: 5394551 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.3886. Min Act: -0.1700
Data Index: 4158501 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.3886. Min Act: -0.1700
Data Index: 2057200 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.2948. Min Act: -0.1700
Data Index: 4687058 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.3261. Min Act: -0.1700
Data Index: 1344251 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.2948. Min Act: -0.1700
Data Index: 4158658 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.3261. Min Act: -0.1700
Data Index: 3466350 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9511. Min Range: -7.9511
Max Act: 7.3261. Min Act: -0.1700
Data Index: 4397408 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19