Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2165. Min Range: -4.2165
Max Act: 4.2165. Min Act: -0.1700
Data Index: 6016306 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2165. Min Range: -4.2165
Max Act: 4.1853. Min Act: -0.1700
Data Index: 2890128 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2165. Min Range: -4.2165
Max Act: 4.1540. Min Act: -0.1700
Data Index: 2515139 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2165. Min Range: -4.2165
Max Act: 4.0602. Min Act: -0.1700
Data Index: 5154899 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2165. Min Range: -4.2165
Max Act: 4.0134. Min Act: -0.1700
Data Index: 3582773 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2165. Min Range: -4.2165
Max Act: 4.0290. Min Act: -0.1700
Data Index: 7271030 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.9665. Min Act: -0.1700
Data Index: 6999612 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.9508. Min Act: -0.1700
Data Index: 7750380 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.9196. Min Act: -0.1700
Data Index: 7016894 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.9039. Min Act: -0.1700
Data Index: 5774793 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.9039. Min Act: -0.1700
Data Index: 1828137 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.8883. Min Act: -0.1700
Data Index: 1934678 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.8883. Min Act: -0.1700
Data Index: 5984012 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.9039. Min Act: -0.1700
Data Index: 487309 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.8883. Min Act: -0.1700
Data Index: 4600508 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.8727. Min Act: -0.1700
Data Index: 5149902 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.8883. Min Act: -0.1700
Data Index: 4158330 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.8883. Min Act: -0.1700
Data Index: 8646846 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.8727. Min Act: -0.1700
Data Index: 5107954 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2165. Min Range: -4.2165
Max Act: 3.8727. Min Act: -0.1700
Data Index: 2568680 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19