Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 559 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.9265. Min Act: -0.1700
Data Index: 2713552 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.9265. Min Act: -0.1700
Data Index: 5973967 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.9265. Min Act: -0.1700
Data Index: 4274122 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.7390. Min Act: -0.1700
Data Index: 3508503 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.6765. Min Act: -0.1700
Data Index: 5775331 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.8015. Min Act: -0.1700
Data Index: 2408905 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.7390. Min Act: -0.1700
Data Index: 3108023 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.6140. Min Act: -0.1700
Data Index: 7738833 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.6140. Min Act: -0.1700
Data Index: 7508643 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.6140. Min Act: -0.1700
Data Index: 5275794 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.4890. Min Act: -0.1700
Data Index: 341593 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.4890. Min Act: -0.1700
Data Index: 665560 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.4265. Min Act: -0.1700
Data Index: 7577467 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.4265. Min Act: -0.1698
Data Index: 6817012 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.3015. Min Act: -0.1700
Data Index: 511652 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.3640. Min Act: -0.1700
Data Index: 393341 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.3015. Min Act: -0.1700
Data Index: 1470426 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.3015. Min Act: -0.1700
Data Index: 6817013 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.3015. Min Act: -0.1700
Data Index: 2063733 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.9265. Min Range: -14.9265
Max Act: 14.3015. Min Act: -0.1700
Data Index: 3148620 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19