Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6354 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3377. Min Range: -5.3377
Max Act: 5.3377. Min Act: -0.1700
Data Index: 2984875 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3377. Min Range: -5.3377
Max Act: 5.3065. Min Act: -0.1700
Data Index: 5789717 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3377. Min Range: -5.3377
Max Act: 5.1815. Min Act: -0.1700
Data Index: 1614468 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3377. Min Range: -5.3377
Max Act: 5.1190. Min Act: -0.1700
Data Index: 3810980 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3377. Min Range: -5.3377
Max Act: 5.0565. Min Act: -0.1700
Data Index: 6800904 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3377. Min Range: -5.3377
Max Act: 5.0565. Min Act: -0.1700
Data Index: 3973336 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9940. Min Act: -0.1700
Data Index: 2275824 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3377. Min Range: -5.3377
Max Act: 5.0252. Min Act: -0.1700
Data Index: 4718028 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3377. Min Range: -5.3377
Max Act: 5.0252. Min Act: -0.1700
Data Index: 3366001 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9940. Min Act: -0.1700
Data Index: 5928322 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9940. Min Act: -0.1700
Data Index: 7347572 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9940. Min Act: -0.1700
Data Index: 5586232 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9627. Min Act: -0.1700
Data Index: 8003216 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9315. Min Act: -0.1700
Data Index: 7485475 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9315. Min Act: -0.1700
Data Index: 7179243 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9315. Min Act: -0.1700
Data Index: 1547135 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9315. Min Act: -0.1700
Data Index: 5847862 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9315. Min Act: -0.1700
Data Index: 5057433 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9315. Min Act: -0.1700
Data Index: 2985801 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3377. Min Range: -5.3377
Max Act: 4.9002. Min Act: -0.1700
Data Index: 5104092 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19