Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.8321. Min Act: -0.1700
Data Index: 2476871 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.8321. Min Act: -0.1700
Data Index: 6116404 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.7696. Min Act: -0.1700
Data Index: 7650725 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.7383. Min Act: -0.1700
Data Index: 3984179 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.7071. Min Act: -0.1700
Data Index: 7078526 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.7071. Min Act: -0.1700
Data Index: 8351294 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.7071. Min Act: -0.1700
Data Index: 8602505 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6758. Min Act: -0.1700
Data Index: 2710156 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6758. Min Act: -0.1700
Data Index: 233684 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6758. Min Act: -0.1700
Data Index: 1613236 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6758. Min Act: -0.1700
Data Index: 8257860 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6758. Min Act: -0.1700
Data Index: 1287701 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6446. Min Act: -0.1700
Data Index: 914500 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6446. Min Act: -0.1700
Data Index: 4749019 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6133. Min Act: -0.1700
Data Index: 2921489 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6133. Min Act: -0.1700
Data Index: 6967187 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6133. Min Act: -0.1700
Data Index: 2561592 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.6133. Min Act: -0.1700
Data Index: 2010548 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.5821. Min Act: -0.1700
Data Index: 7244493 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8321. Min Range: -4.8321
Max Act: 4.5821. Min Act: -0.1700
Data Index: 3950078 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19