Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3377 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.7383. Min Act: -0.1700
Data Index: 3314591 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.6914. Min Act: -0.1700
Data Index: 8270360 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.6914. Min Act: -0.1700
Data Index: 1193357 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.6601. Min Act: -0.1700
Data Index: 2423731 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.6131. Min Act: -0.1700
Data Index: 2343346 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.5975. Min Act: -0.1700
Data Index: 6022016 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.5975. Min Act: -0.1700
Data Index: 5086104 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.5975. Min Act: -0.1700
Data Index: 8391512 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.5192. Min Act: -0.1700
Data Index: 3200381 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.5505. Min Act: -0.1700
Data Index: 2216773 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.5349. Min Act: -0.1700
Data Index: 497370 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.5035. Min Act: -0.1700
Data Index: 6238820 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.4879. Min Act: -0.1700
Data Index: 2440497 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.4722. Min Act: -0.1700
Data Index: 3649599 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.4879. Min Act: -0.1700
Data Index: 7140435 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.4409. Min Act: -0.1700
Data Index: 3523998 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.4409. Min Act: -0.1700
Data Index: 5252846 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.4252. Min Act: -0.1700
Data Index: 8083319 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.4252. Min Act: -0.1700
Data Index: 4670524 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7383. Min Range: -3.7383
Max Act: 3.4252. Min Act: -0.1700
Data Index: 1870464 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19