Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2122. Min Range: -4.2122
Max Act: 4.2122. Min Act: -0.1700
Data Index: 6330791 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2122. Min Range: -4.2122
Max Act: 4.1497. Min Act: -0.1700
Data Index: 1389244 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2122. Min Range: -4.2122
Max Act: 4.1185. Min Act: -0.1700
Data Index: 6406267 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2122. Min Range: -4.2122
Max Act: 4.0872. Min Act: -0.1700
Data Index: 4731727 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2122. Min Range: -4.2122
Max Act: 4.0560. Min Act: -0.1700
Data Index: 4821284 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2122. Min Range: -4.2122
Max Act: 4.0560. Min Act: -0.1700
Data Index: 1785226 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2122. Min Range: -4.2122
Max Act: 4.0247. Min Act: -0.1700
Data Index: 8824202 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.9622. Min Act: -0.1700
Data Index: 4419566 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.9309. Min Act: -0.1700
Data Index: 3099275 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.8684. Min Act: -0.1700
Data Index: 7882501 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.8684. Min Act: -0.1700
Data Index: 527590 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.8371. Min Act: -0.1700
Data Index: 4167959 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.8371. Min Act: -0.1700
Data Index: 518255 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.8371. Min Act: -0.1700
Data Index: 55179 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.8371. Min Act: -0.1700
Data Index: 7395520 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.7746. Min Act: -0.1700
Data Index: 980907 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.8058. Min Act: -0.1700
Data Index: 8041901 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.8058. Min Act: -0.1700
Data Index: 794218 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.8058. Min Act: -0.1700
Data Index: 7206171 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2122. Min Range: -4.2122
Max Act: 3.7746. Min Act: -0.1700
Data Index: 445444 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19