Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.5177. Min Act: -0.1700
Data Index: 3785893 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.5020. Min Act: -0.1699
Data Index: 8590719 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.4864. Min Act: -0.1700
Data Index: 121323 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.4551. Min Act: -0.1700
Data Index: 3117873 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.4394. Min Act: -0.1700
Data Index: 3451961 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.4394. Min Act: -0.1700
Data Index: 7199835 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.4394. Min Act: -0.1700
Data Index: 3785897 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.4237. Min Act: -0.1700
Data Index: 7221662 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.4237. Min Act: -0.1700
Data Index: 2584773 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.3924. Min Act: -0.1700
Data Index: 2978927 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.3924. Min Act: -0.1700
Data Index: 3785890 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.3767. Min Act: -0.1686
Data Index: 2156315 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.3610. Min Act: -0.1700
Data Index: 3967730 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.3453. Min Act: -0.1700
Data Index: 2646706 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.3296. Min Act: -0.1700
Data Index: 4796381 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.3139. Min Act: -0.1700
Data Index: 3817816 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.2982. Min Act: -0.1700
Data Index: 2156314 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.2982. Min Act: -0.1700
Data Index: 3224724 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.2982. Min Act: -0.1700
Data Index: 4506326 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5177. Min Range: -3.5177
Max Act: 3.2982. Min Act: -0.1700
Data Index: 5024541 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19