Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 949 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.6814. Min Act: -0.1700
Data Index: 2473846 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.6814. Min Act: -0.1700
Data Index: 6957332 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.6189. Min Act: -0.1700
Data Index: 8022507 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.6189. Min Act: -0.1700
Data Index: 7579844 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.5876. Min Act: -0.1700
Data Index: 4787915 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.4939. Min Act: -0.1700
Data Index: 6220429 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.5251. Min Act: -0.1700
Data Index: 7376264 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.4939. Min Act: -0.1700
Data Index: 7856813 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.4939. Min Act: -0.1700
Data Index: 1876087 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.5564. Min Act: -0.1700
Data Index: 8433067 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.6189. Min Act: -0.1700
Data Index: 1791320 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.4939. Min Act: -0.1700
Data Index: 6249746 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.4626. Min Act: -0.1700
Data Index: 5943432 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.5564. Min Act: -0.1700
Data Index: 3354454 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.5251. Min Act: -0.1700
Data Index: 4242140 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.4626. Min Act: -0.1700
Data Index: 6992585 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.5251. Min Act: -0.1700
Data Index: 3622147 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.4939. Min Act: -0.1700
Data Index: 6227532 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.4626. Min Act: -0.1700
Data Index: 6212133 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6814. Min Range: -4.6814
Max Act: 4.5251. Min Act: -0.1700
Data Index: 59637 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19