Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3727 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0239. Min Range: -5.0239
Max Act: 5.0239. Min Act: -0.1700
Data Index: 6575423 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.8989. Min Act: -0.1700
Data Index: 717261 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.8052. Min Act: -0.1700
Data Index: 349045 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.8052. Min Act: -0.1700
Data Index: 6816840 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7739. Min Act: -0.1700
Data Index: 8406362 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7739. Min Act: -0.1700
Data Index: 3750513 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7427. Min Act: -0.1700
Data Index: 5271892 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7427. Min Act: -0.1700
Data Index: 7536152 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7427. Min Act: -0.1700
Data Index: 2872465 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7427. Min Act: -0.1700
Data Index: 5425281 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7427. Min Act: -0.1700
Data Index: 5189584 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7427. Min Act: -0.1700
Data Index: 6090270 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7114. Min Act: -0.1700
Data Index: 5069427 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7114. Min Act: -0.1700
Data Index: 7041583 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.7114. Min Act: -0.1700
Data Index: 8209906 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6802. Min Act: -0.1700
Data Index: 6428708 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6802. Min Act: -0.1700
Data Index: 6400842 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6802. Min Act: -0.1700
Data Index: 4194684 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6802. Min Act: -0.1700
Data Index: 5647997 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6802. Min Act: -0.1700
Data Index: 8393735 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19