Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4105. Min Range: -5.4105
Max Act: 5.4105. Min Act: -0.1700
Data Index: 3794477 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4105. Min Range: -5.4105
Max Act: 5.2230. Min Act: -0.1700
Data Index: 7930473 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4105. Min Range: -5.4105
Max Act: 5.1917. Min Act: -0.1700
Data Index: 1425862 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4105. Min Range: -5.4105
Max Act: 5.1917. Min Act: -0.1700
Data Index: 5849606 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4105. Min Range: -5.4105
Max Act: 5.1292. Min Act: -0.1700
Data Index: 173095 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4105. Min Range: -5.4105
Max Act: 5.0355. Min Act: -0.1700
Data Index: 42818 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4105. Min Range: -5.4105
Max Act: 5.0355. Min Act: -0.1700
Data Index: 7240193 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4105. Min Range: -5.4105
Max Act: 5.0042. Min Act: -0.1700
Data Index: 3567102 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.9105. Min Act: -0.1700
Data Index: 5258255 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.9417. Min Act: -0.1700
Data Index: 4039056 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.8792. Min Act: -0.1700
Data Index: 2113102 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.8792. Min Act: -0.1700
Data Index: 1169525 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.8792. Min Act: -0.1700
Data Index: 8192186 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.8792. Min Act: -0.1700
Data Index: 1664818 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.8792. Min Act: -0.1700
Data Index: 5586126 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.8480. Min Act: -0.1700
Data Index: 2222963 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.8480. Min Act: -0.1700
Data Index: 7507127 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.8480. Min Act: -0.1700
Data Index: 2810333 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.8480. Min Act: -0.1700
Data Index: 7530466 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4105. Min Range: -5.4105
Max Act: 4.8480. Min Act: -0.1700
Data Index: 2272212 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19