Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5497 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.8819. Min Act: -0.1700
Data Index: 6362784 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.6006. Min Act: -0.1700
Data Index: 5403203 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.5381. Min Act: -0.1700
Data Index: 3084454 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.4756. Min Act: -0.1700
Data Index: 4580306 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.4131. Min Act: -0.1700
Data Index: 1321729 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.4131. Min Act: -0.1700
Data Index: 7182851 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.3194. Min Act: -0.1700
Data Index: 4803579 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.2256. Min Act: -0.1700
Data Index: 793747 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.1944. Min Act: -0.1700
Data Index: 7957340 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.1944. Min Act: -0.1700
Data Index: 2248169 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.2256. Min Act: -0.1700
Data Index: 7437296 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.1631. Min Act: -0.1700
Data Index: 269294 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.1944. Min Act: -0.1700
Data Index: 1521704 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.0381. Min Act: -0.1700
Data Index: 390143 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.0694. Min Act: -0.1700
Data Index: 8720325 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.0381. Min Act: -0.1700
Data Index: 7645343 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.0694. Min Act: -0.1700
Data Index: 3206887 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.0694. Min Act: -0.1700
Data Index: 2098271 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.0381. Min Act: -0.1700
Data Index: 3007364 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8819. Min Range: -7.8819
Max Act: 7.0381. Min Act: -0.1700
Data Index: 8595311 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19