Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2752 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3423. Min Range: -6.3423
Max Act: 6.3423. Min Act: -0.1700
Data Index: 3095473 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3423. Min Range: -6.3423
Max Act: 6.2485. Min Act: -0.1700
Data Index: 2890679 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3423. Min Range: -6.3423
Max Act: 6.1235. Min Act: -0.1700
Data Index: 1349409 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3423. Min Range: -6.3423
Max Act: 6.0923. Min Act: -0.1700
Data Index: 391076 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3423. Min Range: -6.3423
Max Act: 6.0610. Min Act: -0.1700
Data Index: 7661858 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3423. Min Range: -6.3423
Max Act: 6.0298. Min Act: -0.1700
Data Index: 1412778 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3423. Min Range: -6.3423
Max Act: 6.0298. Min Act: -0.1700
Data Index: 5897696 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9985. Min Act: -0.1700
Data Index: 4777586 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9985. Min Act: -0.1700
Data Index: 4612521 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3423. Min Range: -6.3423
Max Act: 6.0298. Min Act: -0.1700
Data Index: 3900329 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9985. Min Act: -0.1700
Data Index: 5383915 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9360. Min Act: -0.1700
Data Index: 3530228 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9673. Min Act: -0.1700
Data Index: 3636817 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9360. Min Act: -0.1700
Data Index: 6759892 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9360. Min Act: -0.1700
Data Index: 320451 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9048. Min Act: -0.1700
Data Index: 5697887 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9048. Min Act: -0.1700
Data Index: 4392955 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.8735. Min Act: -0.1700
Data Index: 4910073 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9048. Min Act: -0.1700
Data Index: 2248334 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3423. Min Range: -6.3423
Max Act: 5.9048. Min Act: -0.1700
Data Index: 3344692 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19