Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2224 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0308. Min Range: -5.0308
Max Act: 5.0308. Min Act: -0.1700
Data Index: 417401 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.9370. Min Act: -0.1700
Data Index: 4851287 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.8120. Min Act: -0.1700
Data Index: 6675473 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.7495. Min Act: -0.1700
Data Index: 6255089 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.7183. Min Act: -0.1700
Data Index: 2765454 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.7495. Min Act: -0.1700
Data Index: 2896350 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.7183. Min Act: -0.1700
Data Index: 6918957 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.7183. Min Act: -0.1700
Data Index: 1238148 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.7183. Min Act: -0.1700
Data Index: 1164092 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6870. Min Act: -0.1700
Data Index: 1320043 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6870. Min Act: -0.1700
Data Index: 5332564 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6558. Min Act: -0.1700
Data Index: 4598658 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6558. Min Act: -0.1700
Data Index: 5436245 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6558. Min Act: -0.1700
Data Index: 8557778 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6558. Min Act: -0.1700
Data Index: 8705080 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.6245. Min Act: -0.1700
Data Index: 4416225 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5933. Min Act: -0.1700
Data Index: 3296471 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5933. Min Act: -0.1700
Data Index: 1363556 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5933. Min Act: -0.1700
Data Index: 3373926 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0308. Min Range: -5.0308
Max Act: 4.5620. Min Act: -0.1700
Data Index: 6147662 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19