Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1912 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.3049. Min Act: -0.1700
Data Index: 2384810 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.2264. Min Act: -0.1700
Data Index: 196601 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.1949. Min Act: -0.1700
Data Index: 5288299 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.1320. Min Act: -0.1700
Data Index: 854063 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.1477. Min Act: -0.1700
Data Index: 6597631 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.1320. Min Act: -0.1700
Data Index: 7925289 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.0689. Min Act: -0.1700
Data Index: 4254575 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.0689. Min Act: -0.1700
Data Index: 350127 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.0374. Min Act: -0.1700
Data Index: 4835152 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.0374. Min Act: -0.1700
Data Index: 8037811 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.0374. Min Act: -0.1700
Data Index: 3817920 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.0374. Min Act: -0.1700
Data Index: 8156352 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.0216. Min Act: -0.1700
Data Index: 854060 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.0216. Min Act: -0.1700
Data Index: 3747050 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.0216. Min Act: -0.1700
Data Index: 854061 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3049. Min Range: -3.3049
Max Act: 3.0058. Min Act: -0.1700
Data Index: 4543110 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3049. Min Range: -3.3049
Max Act: 2.9900. Min Act: -0.1700
Data Index: 3957177 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3049. Min Range: -3.3049
Max Act: 2.9900. Min Act: -0.1700
Data Index: 3817922 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3049. Min Range: -3.3049
Max Act: 2.9900. Min Act: -0.1700
Data Index: 5631930 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3049. Min Range: -3.3049
Max Act: 2.9900. Min Act: -0.1700
Data Index: 8208729 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19