Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.9866. Min Act: -0.1700
Data Index: 2552450 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.8147. Min Act: -0.1700
Data Index: 905250 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.7834. Min Act: -0.1700
Data Index: 3420585 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.7834. Min Act: -0.1700
Data Index: 7942625 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.7365. Min Act: -0.1700
Data Index: 2914703 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6739. Min Act: -0.1700
Data Index: 3807206 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6896. Min Act: -0.1700
Data Index: 8340602 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.7052. Min Act: -0.1700
Data Index: 3713798 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6583. Min Act: -0.1700
Data Index: 3155908 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6270. Min Act: -0.1700
Data Index: 150448 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6270. Min Act: -0.1700
Data Index: 805614 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6426. Min Act: -0.1700
Data Index: 5268960 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6583. Min Act: -0.1700
Data Index: 3796110 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5957. Min Act: -0.1700
Data Index: 4086964 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6113. Min Act: -0.1700
Data Index: 8149965 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6426. Min Act: -0.1700
Data Index: 3991798 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6113. Min Act: -0.1700
Data Index: 7486707 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5957. Min Act: -0.1700
Data Index: 4810974 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6113. Min Act: -0.1700
Data Index: 4990126 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5644. Min Act: -0.1700
Data Index: 3796109 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19