Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2913 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.9803. Min Act: -0.1700
Data Index: 2499927 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.8553. Min Act: -0.1700
Data Index: 1922163 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.7928. Min Act: -0.1700
Data Index: 3215300 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.7928. Min Act: -0.1700
Data Index: 7014303 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.7615. Min Act: -0.1700
Data Index: 1406577 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.7615. Min Act: -0.1700
Data Index: 6140091 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.7303. Min Act: -0.1700
Data Index: 1742730 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6990. Min Act: -0.1700
Data Index: 3667801 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6990. Min Act: -0.1700
Data Index: 6279976 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6990. Min Act: -0.1700
Data Index: 2097725 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.7303. Min Act: -0.1700
Data Index: 6263300 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6990. Min Act: -0.1700
Data Index: 8562201 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6678. Min Act: -0.1700
Data Index: 5452360 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6678. Min Act: -0.1700
Data Index: 2192281 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6365. Min Act: -0.1700
Data Index: 6563259 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6678. Min Act: -0.1700
Data Index: 4269830 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6365. Min Act: -0.1700
Data Index: 8705951 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6365. Min Act: -0.1700
Data Index: 1124397 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6365. Min Act: -0.1700
Data Index: 7709151 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9803. Min Range: -5.9803
Max Act: 5.6053. Min Act: -0.1700
Data Index: 7261926 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19