Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2264 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0146. Min Range: -5.0146
Max Act: 5.0146. Min Act: -0.1700
Data Index: 692459 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0146. Min Range: -5.0146
Max Act: 5.0146. Min Act: -0.1700
Data Index: 6356635 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.9834. Min Act: -0.1700
Data Index: 2868156 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0146. Min Range: -5.0146
Max Act: 5.0146. Min Act: -0.1700
Data Index: 6134102 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.9521. Min Act: -0.1700
Data Index: 8313782 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.8896. Min Act: -0.1700
Data Index: 2173123 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.8896. Min Act: -0.1700
Data Index: 3841727 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.8584. Min Act: -0.1700
Data Index: 8249012 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.8584. Min Act: -0.1700
Data Index: 7830780 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.8271. Min Act: -0.1700
Data Index: 4478625 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.7646. Min Act: -0.1700
Data Index: 2239711 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.7646. Min Act: -0.1700
Data Index: 264196 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.7646. Min Act: -0.1700
Data Index: 3454399 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.7646. Min Act: -0.1700
Data Index: 1101105 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.7021. Min Act: -0.1700
Data Index: 4953829 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.7334. Min Act: -0.1700
Data Index: 8686018 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.7021. Min Act: -0.1700
Data Index: 3599140 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.7021. Min Act: -0.1700
Data Index: 1440298 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.6709. Min Act: -0.1700
Data Index: 700438 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0146. Min Range: -5.0146
Max Act: 4.6709. Min Act: -0.1700
Data Index: 4631147 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19