Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1959 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6010. Min Range: -9.6010
Max Act: 9.6010. Min Act: -0.1700
Data Index: 7104520 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6010. Min Range: -9.6010
Max Act: 9.1010. Min Act: -0.1700
Data Index: 2978691 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6010. Min Range: -9.6010
Max Act: 9.1010. Min Act: -0.1700
Data Index: 7233926 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.9760. Min Act: -0.1700
Data Index: 7104251 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.9760. Min Act: -0.1700
Data Index: 6214445 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.9135. Min Act: -0.1700
Data Index: 2637018 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.8510. Min Act: -0.1700
Data Index: 5149340 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.7885. Min Act: -0.1700
Data Index: 949579 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.8510. Min Act: -0.1700
Data Index: 2024605 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.7260. Min Act: -0.1700
Data Index: 3501788 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.7260. Min Act: -0.1700
Data Index: 7165384 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.7260. Min Act: -0.1700
Data Index: 7310967 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.6635. Min Act: -0.1700
Data Index: 6357550 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.6635. Min Act: -0.1700
Data Index: 3183546 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.6635. Min Act: -0.1700
Data Index: 2809131 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.6635. Min Act: -0.1700
Data Index: 3191999 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.7260. Min Act: -0.1700
Data Index: 2983033 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.6635. Min Act: -0.1700
Data Index: 1450126 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.6635. Min Act: -0.1700
Data Index: 1630373 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6010. Min Range: -9.6010
Max Act: 8.6635. Min Act: -0.1700
Data Index: 1495593 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19