Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6366 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4842. Min Act: -0.1700
Data Index: 7101562 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4998. Min Act: -0.1700
Data Index: 8371701 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4998. Min Act: -0.1700
Data Index: 7291440 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4842. Min Act: -0.1700
Data Index: 6154262 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4842. Min Act: -0.1700
Data Index: 37396 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4528. Min Act: -0.1700
Data Index: 7328882 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4528. Min Act: -0.1700
Data Index: 2335059 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4372. Min Act: -0.1700
Data Index: 1679168 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4372. Min Act: -0.1700
Data Index: 6251864 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4372. Min Act: -0.1700
Data Index: 3767834 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4372. Min Act: -0.1700
Data Index: 7944500 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4372. Min Act: -0.1700
Data Index: 3646947 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4215. Min Act: -0.1700
Data Index: 8100936 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4215. Min Act: -0.1700
Data Index: 2237538 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4215. Min Act: -0.1700
Data Index: 2486176 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4215. Min Act: -0.1700
Data Index: 5441418 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4372. Min Act: -0.1700
Data Index: 3579175 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4215. Min Act: -0.1700
Data Index: 8563130 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4058. Min Act: -0.1700
Data Index: 8639313 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4998. Min Range: -3.4998
Max Act: 3.4215. Min Act: -0.1700
Data Index: 6458536 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19