Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1028 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0421. Min Range: -5.0421
Max Act: 5.0421. Min Act: -0.1700
Data Index: 8481721 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.9796. Min Act: -0.1700
Data Index: 5059798 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.9171. Min Act: -0.1700
Data Index: 8568259 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8858. Min Act: -0.1700
Data Index: 3140797 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8858. Min Act: -0.1700
Data Index: 821741 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8858. Min Act: -0.1700
Data Index: 7446716 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8546. Min Act: -0.1700
Data Index: 407207 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8546. Min Act: -0.1700
Data Index: 498494 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8233. Min Act: -0.1700
Data Index: 145135 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8546. Min Act: -0.1700
Data Index: 4171990 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8546. Min Act: -0.1700
Data Index: 3461854 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8233. Min Act: -0.1700
Data Index: 361220 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.7921. Min Act: -0.1700
Data Index: 7249543 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.7921. Min Act: -0.1700
Data Index: 2116765 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.7921. Min Act: -0.1700
Data Index: 1697205 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8233. Min Act: -0.1700
Data Index: 3165269 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.8233. Min Act: -0.1700
Data Index: 3165270 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.7921. Min Act: -0.1700
Data Index: 7242113 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.7608. Min Act: -0.1700
Data Index: 4975160 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.7608. Min Act: -0.1700
Data Index: 6662001 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19