Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.4901. Min Act: -0.1700
Data Index: 2525641 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.3963. Min Act: -0.1700
Data Index: 5116612 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.3651. Min Act: -0.1700
Data Index: 2293034 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.3338. Min Act: -0.1700
Data Index: 4270982 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.3026. Min Act: -0.1700
Data Index: 2725594 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.2401. Min Act: -0.1700
Data Index: 7951529 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.2713. Min Act: -0.1700
Data Index: 3737699 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.2088. Min Act: -0.1700
Data Index: 6245076 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.2088. Min Act: -0.1700
Data Index: 2747691 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.2088. Min Act: -0.1700
Data Index: 791065 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.2088. Min Act: -0.1700
Data Index: 5898572 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.2088. Min Act: -0.1700
Data Index: 8375846 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.1776. Min Act: -0.1700
Data Index: 7342016 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.1776. Min Act: -0.1700
Data Index: 81035 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.1776. Min Act: -0.1700
Data Index: 7674811 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.1776. Min Act: -0.1700
Data Index: 391916 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.1463. Min Act: -0.1700
Data Index: 36334 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.1463. Min Act: -0.1700
Data Index: 1657335 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.1151. Min Act: -0.1700
Data Index: 7348843 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4901. Min Range: -4.4901
Max Act: 4.1151. Min Act: -0.1700
Data Index: 7233649 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19