Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0958. Min Act: -0.1700
Data Index: 4962523 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0958. Min Act: -0.1700
Data Index: 5205722 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0646. Min Act: -0.1700
Data Index: 1494097 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0646. Min Act: -0.1700
Data Index: 3290068 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0646. Min Act: -0.1699
Data Index: 5074904 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0333. Min Act: -0.1700
Data Index: 3056909 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0646. Min Act: -0.1700
Data Index: 696675 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0646. Min Act: -0.1700
Data Index: 2044496 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0333. Min Act: -0.1700
Data Index: 8476389 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0333. Min Act: -0.1700
Data Index: 482365 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0021. Min Act: -0.1700
Data Index: 5295847 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0333. Min Act: -0.1700
Data Index: 1598062 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0021. Min Act: -0.1700
Data Index: 3008175 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0021. Min Act: -0.1700
Data Index: 2932505 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0021. Min Act: -0.1700
Data Index: 2916006 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0021. Min Act: -0.1700
Data Index: 631134 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0333. Min Act: -0.1700
Data Index: 1300452 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0958. Min Range: -5.0958
Max Act: 4.9708. Min Act: -0.1700
Data Index: 779786 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0021. Min Act: -0.1700
Data Index: 4443262 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0958. Min Range: -5.0958
Max Act: 5.0021. Min Act: -0.1700
Data Index: 4546 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19