Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 747 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.7668. Min Act: -0.1700
Data Index: 1436756 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.6418. Min Act: -0.1700
Data Index: 2691865 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.4856. Min Act: -0.1700
Data Index: 3398779 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.4856. Min Act: -0.1700
Data Index: 4111020 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.4231. Min Act: -0.1700
Data Index: 3888946 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.3606. Min Act: -0.1700
Data Index: 8129391 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.3606. Min Act: -0.1700
Data Index: 3272351 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.3606. Min Act: -0.1700
Data Index: 8810067 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.2981. Min Act: -0.1700
Data Index: 1224793 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.3293. Min Act: -0.1700
Data Index: 6688611 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.3293. Min Act: -0.1700
Data Index: 7466312 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.3293. Min Act: -0.1700
Data Index: 3855291 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.2981. Min Act: -0.1700
Data Index: 6951814 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.2981. Min Act: -0.1700
Data Index: 8542114 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.2981. Min Act: -0.1700
Data Index: 3659368 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.2981. Min Act: -0.1700
Data Index: 7622053 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.2981. Min Act: -0.1700
Data Index: 3313358 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.2981. Min Act: -0.1700
Data Index: 2451965 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.2981. Min Act: -0.1700
Data Index: 1214777 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7668. Min Range: -5.7668
Max Act: 5.2668. Min Act: -0.1700
Data Index: 2916740 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19