Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 258 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.8686. Min Act: -0.1700
Data Index: 644053 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.7124. Min Act: -0.1700
Data Index: 644055 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.7124. Min Act: -0.1700
Data Index: 644054 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.5249. Min Act: -0.1700
Data Index: 644052 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.4311. Min Act: -0.1700
Data Index: 4597370 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.3061. Min Act: -0.1700
Data Index: 5511886 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.2124. Min Act: -0.1700
Data Index: 7883339 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.2436. Min Act: -0.1700
Data Index: 2112533 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.2124. Min Act: -0.1700
Data Index: 4575975 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.1811. Min Act: -0.1700
Data Index: 977759 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.2124. Min Act: -0.1700
Data Index: 7729607 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.1811. Min Act: -0.1700
Data Index: 8176010 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.1811. Min Act: -0.1700
Data Index: 1289773 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.1499. Min Act: -0.1700
Data Index: 1168396 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.1499. Min Act: -0.1700
Data Index: 4524091 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.0874. Min Act: -0.1700
Data Index: 5791615 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.0874. Min Act: -0.1700
Data Index: 7883337 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.0561. Min Act: -0.1700
Data Index: 7883345 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.0561. Min Act: -0.1700
Data Index: 8553848 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8686. Min Range: -5.8686
Max Act: 5.0561. Min Act: -0.1700
Data Index: 2970004 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19