Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1101 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3995. Min Range: -8.3995
Max Act: 8.3995. Min Act: -0.1700
Data Index: 4984947 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3995. Min Range: -8.3995
Max Act: 8.1495. Min Act: -0.1700
Data Index: 7317015 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3995. Min Range: -8.3995
Max Act: 8.0245. Min Act: -0.1700
Data Index: 780515 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.9620. Min Act: -0.1700
Data Index: 2031510 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.9620. Min Act: -0.1700
Data Index: 7160503 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.8370. Min Act: -0.1700
Data Index: 799168 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.8370. Min Act: -0.1700
Data Index: 4732622 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.8370. Min Act: -0.1700
Data Index: 2598819 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.7120. Min Act: -0.1700
Data Index: 6027960 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.7120. Min Act: -0.1700
Data Index: 4778277 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.6495. Min Act: -0.1700
Data Index: 8558394 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.6495. Min Act: -0.1700
Data Index: 1331287 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.6495. Min Act: -0.1700
Data Index: 7106971 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.6495. Min Act: -0.1700
Data Index: 351221 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.5870. Min Act: -0.1700
Data Index: 5144470 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.5245. Min Act: -0.1700
Data Index: 3580316 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.5245. Min Act: -0.1700
Data Index: 1240425 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.5558. Min Act: -0.1700
Data Index: 5108645 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.4933. Min Act: -0.1700
Data Index: 3610700 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3995. Min Range: -8.3995
Max Act: 7.4933. Min Act: -0.1700
Data Index: 71571 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19