Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.8680. Min Act: -0.1700
Data Index: 1453583 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.8367. Min Act: -0.1700
Data Index: 8351365 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.8055. Min Act: -0.1700
Data Index: 4876950 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.8055. Min Act: -0.1700
Data Index: 3795102 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.7117. Min Act: -0.1700
Data Index: 4104644 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.7430. Min Act: -0.1700
Data Index: 8199887 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6805. Min Act: -0.1700
Data Index: 3924165 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6805. Min Act: -0.1700
Data Index: 3169956 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.7117. Min Act: -0.1700
Data Index: 3617670 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6805. Min Act: -0.1700
Data Index: 43677 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6805. Min Act: -0.1700
Data Index: 7913451 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6180. Min Act: -0.1700
Data Index: 6799576 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6492. Min Act: -0.1700
Data Index: 5930388 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6180. Min Act: -0.1700
Data Index: 4178290 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6180. Min Act: -0.1700
Data Index: 1571503 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6180. Min Act: -0.1700
Data Index: 6870598 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6492. Min Act: -0.1700
Data Index: 206487 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.5867. Min Act: -0.1700
Data Index: 8432750 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.5867. Min Act: -0.1700
Data Index: 8199886 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8680. Min Range: -5.8680
Max Act: 5.6180. Min Act: -0.1700
Data Index: 2351076 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19