Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5670 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0493. Min Range: -6.0493
Max Act: 6.0493. Min Act: -0.1700
Data Index: 8809847 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.3618. Min Act: -0.1700
Data Index: 7455377 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.3306. Min Act: -0.1700
Data Index: 8641153 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.2993. Min Act: -0.1700
Data Index: 321106 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.2681. Min Act: -0.1700
Data Index: 6231229 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.2681. Min Act: -0.1700
Data Index: 1354823 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.2681. Min Act: -0.1700
Data Index: 5568679 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.2056. Min Act: -0.1700
Data Index: 3933518 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.2368. Min Act: -0.1700
Data Index: 7610777 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.2056. Min Act: -0.1700
Data Index: 988842 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.1743. Min Act: -0.1700
Data Index: 987369 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.1431. Min Act: -0.1700
Data Index: 8756178 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.1431. Min Act: -0.1700
Data Index: 7324128 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 6359577 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 692478 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 4533082 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 7032127 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 3335082 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 7133371 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0493. Min Range: -6.0493
Max Act: 5.0493. Min Act: -0.1700
Data Index: 5684181 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19