Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2339 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1208. Min Range: -5.1208
Max Act: 5.1208. Min Act: -0.1700
Data Index: 6946421 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1208. Min Range: -5.1208
Max Act: 5.0271. Min Act: -0.1700
Data Index: 7895258 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.9958. Min Act: -0.1700
Data Index: 5531511 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.8708. Min Act: -0.1700
Data Index: 6073149 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.8083. Min Act: -0.1700
Data Index: 2084848 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.8083. Min Act: -0.1700
Data Index: 7004250 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7771. Min Act: -0.1700
Data Index: 7892742 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7458. Min Act: -0.1700
Data Index: 3883364 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7458. Min Act: -0.1700
Data Index: 6467551 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7146. Min Act: -0.1700
Data Index: 6556565 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7146. Min Act: -0.1700
Data Index: 3234120 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7146. Min Act: -0.1700
Data Index: 2092664 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7146. Min Act: -0.1700
Data Index: 8178474 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.6833. Min Act: -0.1700
Data Index: 7869347 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.6833. Min Act: -0.1700
Data Index: 7084008 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.6833. Min Act: -0.1700
Data Index: 6322805 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.6833. Min Act: -0.1700
Data Index: 2291361 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.6833. Min Act: -0.1700
Data Index: 5179530 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.6521. Min Act: -0.1700
Data Index: 3426147 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.6521. Min Act: -0.1700
Data Index: 2265683 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19