Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.6901. Min Act: -0.1700
Data Index: 47042 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.5339. Min Act: -0.1700
Data Index: 4102902 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.5339. Min Act: -0.1700
Data Index: 1010513 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.4714. Min Act: -0.1700
Data Index: 3870054 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.3776. Min Act: -0.1700
Data Index: 4721951 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.3776. Min Act: -0.1700
Data Index: 4295455 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.3464. Min Act: -0.1700
Data Index: 5567825 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.2526. Min Act: -0.1700
Data Index: 1469017 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.2526. Min Act: -0.1700
Data Index: 2417622 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.1901. Min Act: -0.1700
Data Index: 6499654 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.2214. Min Act: -0.1700
Data Index: 2694453 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.1901. Min Act: -0.1700
Data Index: 3221409 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.1589. Min Act: -0.1700
Data Index: 2262187 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.1589. Min Act: -0.1700
Data Index: 1033094 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.1276. Min Act: -0.1700
Data Index: 5181736 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.1276. Min Act: -0.1700
Data Index: 2140717 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.1276. Min Act: -0.1700
Data Index: 7262215 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.1589. Min Act: -0.1700
Data Index: 1378275 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.0964. Min Act: -0.1700
Data Index: 1542208 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6901. Min Range: -5.6901
Max Act: 5.0964. Min Act: -0.1700
Data Index: 6278538 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19