Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2656. Min Range: -6.2656
Max Act: 6.2656. Min Act: -0.1700
Data Index: 4415378 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2656. Min Range: -6.2656
Max Act: 6.1094. Min Act: -0.1700
Data Index: 5870645 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2656. Min Range: -6.2656
Max Act: 6.0781. Min Act: -0.1700
Data Index: 7958677 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2656. Min Range: -6.2656
Max Act: 6.0469. Min Act: -0.1700
Data Index: 5246967 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.8906. Min Act: -0.1700
Data Index: 3873750 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.8281. Min Act: -0.1700
Data Index: 643380 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.8594. Min Act: -0.1700
Data Index: 7648696 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.7969. Min Act: -0.1700
Data Index: 2357499 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.7656. Min Act: -0.1700
Data Index: 2040908 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.7656. Min Act: -0.1700
Data Index: 6505590 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.7656. Min Act: -0.1700
Data Index: 6018673 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.7656. Min Act: -0.1700
Data Index: 1235913 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.7344. Min Act: -0.1700
Data Index: 3258593 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.6719. Min Act: -0.1700
Data Index: 2956389 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.6719. Min Act: -0.1700
Data Index: 4090918 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.7031. Min Act: -0.1700
Data Index: 1355953 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.6406. Min Act: -0.1700
Data Index: 4952537 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.6094. Min Act: -0.1700
Data Index: 5961029 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.6094. Min Act: -0.1700
Data Index: 5380107 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2656. Min Range: -6.2656
Max Act: 5.6094. Min Act: -0.1700
Data Index: 2177037 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19