Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3766 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2668. Min Range: -5.2668
Max Act: 5.2668. Min Act: -0.1700
Data Index: 3797355 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2668. Min Range: -5.2668
Max Act: 5.1730. Min Act: -0.1700
Data Index: 1920080 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2668. Min Range: -5.2668
Max Act: 5.1418. Min Act: -0.1700
Data Index: 5649004 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2668. Min Range: -5.2668
Max Act: 5.0168. Min Act: -0.1700
Data Index: 3709957 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2668. Min Range: -5.2668
Max Act: 5.0168. Min Act: -0.1700
Data Index: 3373096 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.9855. Min Act: -0.1700
Data Index: 861680 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.9543. Min Act: -0.1700
Data Index: 1633028 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.9230. Min Act: -0.1700
Data Index: 7176718 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.8918. Min Act: -0.1700
Data Index: 5114237 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.8605. Min Act: -0.1700
Data Index: 6496472 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.8293. Min Act: -0.1700
Data Index: 2396215 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.7668. Min Act: -0.1700
Data Index: 4285030 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.7668. Min Act: -0.1700
Data Index: 640381 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.7980. Min Act: -0.1700
Data Index: 349295 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.7668. Min Act: -0.1700
Data Index: 921346 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.7668. Min Act: -0.1700
Data Index: 4554072 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.7668. Min Act: -0.1700
Data Index: 8732023 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.7668. Min Act: -0.1700
Data Index: 8466829 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.7043. Min Act: -0.1700
Data Index: 2959909 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2668. Min Range: -5.2668
Max Act: 4.7355. Min Act: -0.1700
Data Index: 7526536 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19