Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.9239. Min Act: -0.1700
Data Index: 4142593 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.8301. Min Act: -0.1700
Data Index: 3619601 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.8614. Min Act: -0.1700
Data Index: 7576527 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.8301. Min Act: -0.1700
Data Index: 6091597 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.8301. Min Act: -0.1700
Data Index: 3195613 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.8301. Min Act: -0.1700
Data Index: 8257236 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.7676. Min Act: -0.1700
Data Index: 5152685 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.7989. Min Act: -0.1700
Data Index: 7048528 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.7676. Min Act: -0.1700
Data Index: 4015694 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.7989. Min Act: -0.1700
Data Index: 4541827 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.7676. Min Act: -0.1700
Data Index: 531007 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.7364. Min Act: -0.1700
Data Index: 6082675 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.7051. Min Act: -0.1700
Data Index: 5070692 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.7051. Min Act: -0.1700
Data Index: 2428204 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.7051. Min Act: -0.1700
Data Index: 3519346 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.6739. Min Act: -0.1700
Data Index: 5864869 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.6426. Min Act: -0.1700
Data Index: 5035810 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.6739. Min Act: -0.1700
Data Index: 7879375 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.6739. Min Act: -0.1700
Data Index: 1676860 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9239. Min Range: -4.9239
Max Act: 4.6739. Min Act: -0.1700
Data Index: 4503072 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19