Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.5838. Min Act: -0.1700
Data Index: 5172568 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.4900. Min Act: -0.1700
Data Index: 2730355 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.4275. Min Act: -0.1700
Data Index: 994758 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.3963. Min Act: -0.1700
Data Index: 817234 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.3963. Min Act: -0.1700
Data Index: 1053079 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.3963. Min Act: -0.1700
Data Index: 2965174 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.3025. Min Act: -0.1700
Data Index: 4879171 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.2713. Min Act: -0.1700
Data Index: 2683017 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.2088. Min Act: -0.1700
Data Index: 4066470 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.2400. Min Act: -0.1700
Data Index: 3914603 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.2088. Min Act: -0.1700
Data Index: 1090069 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.1775. Min Act: -0.1700
Data Index: 7498630 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.1775. Min Act: -0.1700
Data Index: 2971351 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.1775. Min Act: -0.1700
Data Index: 2722755 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.1775. Min Act: -0.1700
Data Index: 1699722 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.1463. Min Act: -0.1700
Data Index: 1967707 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.1463. Min Act: -0.1700
Data Index: 6035241 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.1775. Min Act: -0.1700
Data Index: 4733612 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.1463. Min Act: -0.1700
Data Index: 4307774 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5838. Min Range: -6.5838
Max Act: 6.0838. Min Act: -0.1700
Data Index: 1723947 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19