Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2486 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.9556. Min Act: -0.1700
Data Index: 7967974 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.7681. Min Act: -0.1700
Data Index: 2636851 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.7368. Min Act: -0.1700
Data Index: 1616417 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.6743. Min Act: -0.1700
Data Index: 6698318 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.7056. Min Act: -0.1700
Data Index: 3258852 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.6431. Min Act: -0.1700
Data Index: 5981637 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.6431. Min Act: -0.1700
Data Index: 6663968 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.6743. Min Act: -0.1700
Data Index: 7857042 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.6118. Min Act: -0.1700
Data Index: 116807 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.5493. Min Act: -0.1700
Data Index: 4736166 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.5806. Min Act: -0.1700
Data Index: 2967327 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.6118. Min Act: -0.1700
Data Index: 5946614 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.5493. Min Act: -0.1700
Data Index: 3916836 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.5806. Min Act: -0.1700
Data Index: 7394274 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.5806. Min Act: -0.1700
Data Index: 4728708 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.5181. Min Act: -0.1700
Data Index: 3441424 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.5493. Min Act: -0.1700
Data Index: 6354214 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.5806. Min Act: -0.1700
Data Index: 8612666 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.5181. Min Act: -0.1700
Data Index: 6939367 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9556. Min Range: -4.9556
Max Act: 4.5181. Min Act: -0.1700
Data Index: 5340063 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19