Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1803 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2557. Min Range: -5.2557
Max Act: 5.2557. Min Act: -0.1700
Data Index: 5193275 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2557. Min Range: -5.2557
Max Act: 5.1307. Min Act: -0.1700
Data Index: 4151791 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2557. Min Range: -5.2557
Max Act: 5.0994. Min Act: -0.1700
Data Index: 6151055 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2557. Min Range: -5.2557
Max Act: 5.0682. Min Act: -0.1700
Data Index: 5633702 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2557. Min Range: -5.2557
Max Act: 5.0369. Min Act: -0.1700
Data Index: 3116087 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2557. Min Range: -5.2557
Max Act: 5.0057. Min Act: -0.1700
Data Index: 1900703 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2557. Min Range: -5.2557
Max Act: 5.0057. Min Act: -0.1700
Data Index: 5862262 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9744. Min Act: -0.1700
Data Index: 279954 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9744. Min Act: -0.1700
Data Index: 2620005 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9744. Min Act: -0.1700
Data Index: 3770953 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9744. Min Act: -0.1700
Data Index: 4631597 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9744. Min Act: -0.1700
Data Index: 267975 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9432. Min Act: -0.1700
Data Index: 5482401 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9119. Min Act: -0.1700
Data Index: 4712495 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9119. Min Act: -0.1700
Data Index: 5421321 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9119. Min Act: -0.1700
Data Index: 6606767 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9119. Min Act: -0.1700
Data Index: 7172270 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9119. Min Act: -0.1700
Data Index: 480393 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.9119. Min Act: -0.1700
Data Index: 5775151 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2557. Min Range: -5.2557
Max Act: 4.8807. Min Act: -0.1700
Data Index: 5213089 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19