Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.3795. Min Act: -0.1700
Data Index: 5082482 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.3482. Min Act: -0.1698
Data Index: 3944167 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.3170. Min Act: -0.1700
Data Index: 8089758 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.2545. Min Act: -0.1700
Data Index: 4914171 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.2232. Min Act: -0.1681
Data Index: 4822748 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.1920. Min Act: -0.1700
Data Index: 6680169 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.1920. Min Act: -0.1700
Data Index: 3012925 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.1607. Min Act: -0.1700
Data Index: 1595334 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.1295. Min Act: -0.1700
Data Index: 2038557 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.1607. Min Act: -0.1698
Data Index: 7362630 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.1295. Min Act: -0.1700
Data Index: 6540445 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.1607. Min Act: -0.1699
Data Index: 473172 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.1295. Min Act: -0.1700
Data Index: 2517200 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.0982. Min Act: -0.1700
Data Index: 8663800 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.0982. Min Act: -0.1700
Data Index: 1228521 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.0982. Min Act: -0.1700
Data Index: 266062 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.0982. Min Act: -0.1700
Data Index: 7418980 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.0670. Min Act: -0.1699
Data Index: 1282889 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.0670. Min Act: -0.1699
Data Index: 7374265 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3795. Min Range: -5.3795
Max Act: 5.0670. Min Act: -0.1700
Data Index: 4437118 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19