Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1084 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2458. Min Range: -6.2458
Max Act: 6.2458. Min Act: -0.1700
Data Index: 7169762 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2458. Min Range: -6.2458
Max Act: 6.1833. Min Act: -0.1700
Data Index: 2809144 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2458. Min Range: -6.2458
Max Act: 6.0271. Min Act: -0.1700
Data Index: 7831291 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2458. Min Range: -6.2458
Max Act: 6.0271. Min Act: -0.1700
Data Index: 1917393 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.9333. Min Act: -0.1700
Data Index: 4600418 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.9333. Min Act: -0.1700
Data Index: 6828031 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.8708. Min Act: -0.1700
Data Index: 3859032 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.8708. Min Act: -0.1700
Data Index: 8003314 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.8708. Min Act: -0.1700
Data Index: 4142938 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.8396. Min Act: -0.1700
Data Index: 6005078 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.8083. Min Act: -0.1700
Data Index: 1511141 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.8083. Min Act: -0.1700
Data Index: 1707595 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.8396. Min Act: -0.1700
Data Index: 7265236 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.8083. Min Act: -0.1700
Data Index: 492130 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.7771. Min Act: -0.1700
Data Index: 170715 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.7771. Min Act: -0.1700
Data Index: 3081558 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.7458. Min Act: -0.1700
Data Index: 3741037 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.7458. Min Act: -0.1700
Data Index: 7348680 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.7146. Min Act: -0.1700
Data Index: 2768017 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2458. Min Range: -6.2458
Max Act: 5.7458. Min Act: -0.1700
Data Index: 1034680 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19