Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1920 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1463. Min Range: -5.1463
Max Act: 5.1463. Min Act: -0.1700
Data Index: 4321586 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1463. Min Range: -5.1463
Max Act: 5.1463. Min Act: -0.1700
Data Index: 5050223 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1463. Min Range: -5.1463
Max Act: 5.0526. Min Act: -0.1700
Data Index: 1064163 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1463. Min Range: -5.1463
Max Act: 5.0213. Min Act: -0.1700
Data Index: 2293060 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1463. Min Range: -5.1463
Max Act: 5.0526. Min Act: -0.1700
Data Index: 7703636 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1463. Min Range: -5.1463
Max Act: 5.0213. Min Act: -0.1700
Data Index: 5050225 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1463. Min Range: -5.1463
Max Act: 5.0526. Min Act: -0.1700
Data Index: 6535917 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9901. Min Act: -0.1700
Data Index: 7721985 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9588. Min Act: -0.1700
Data Index: 1556662 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9588. Min Act: -0.1700
Data Index: 2734013 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9588. Min Act: -0.1700
Data Index: 235232 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9276. Min Act: -0.1700
Data Index: 3509396 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9276. Min Act: -0.1700
Data Index: 235239 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.8963. Min Act: -0.1700
Data Index: 7501017 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9588. Min Act: -0.1700
Data Index: 2376756 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9276. Min Act: -0.1700
Data Index: 3339067 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9276. Min Act: -0.1700
Data Index: 3281045 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9588. Min Act: -0.1700
Data Index: 7277520 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9276. Min Act: -0.1700
Data Index: 667978 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1463. Min Range: -5.1463
Max Act: 4.9276. Min Act: -0.1700
Data Index: 1064162 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19