Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1091. Min Range: -6.1091
Max Act: 6.1091. Min Act: -0.1700
Data Index: 3129246 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1091. Min Range: -6.1091
Max Act: 6.0466. Min Act: -0.1700
Data Index: 2130216 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1091. Min Range: -6.1091
Max Act: 6.0779. Min Act: -0.1700
Data Index: 5879926 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1091. Min Range: -6.1091
Max Act: 6.0154. Min Act: -0.1700
Data Index: 8648076 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.9529. Min Act: -0.1700
Data Index: 5632219 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.9529. Min Act: -0.1700
Data Index: 2217452 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.9529. Min Act: -0.1700
Data Index: 5338942 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.9216. Min Act: -0.1700
Data Index: 5439869 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.9216. Min Act: -0.1700
Data Index: 7023784 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8904. Min Act: -0.1700
Data Index: 4194852 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8591. Min Act: -0.1700
Data Index: 7132458 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8904. Min Act: -0.1700
Data Index: 5054089 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8591. Min Act: -0.1700
Data Index: 2878827 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8904. Min Act: -0.1700
Data Index: 6351555 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8904. Min Act: -0.1700
Data Index: 8008555 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8904. Min Act: -0.1700
Data Index: 7721287 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8279. Min Act: -0.1700
Data Index: 4953336 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8591. Min Act: -0.1700
Data Index: 2591536 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8279. Min Act: -0.1700
Data Index: 2675847 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1091. Min Range: -6.1091
Max Act: 5.8279. Min Act: -0.1700
Data Index: 8008130 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19