Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3839 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.9533. Min Act: -0.1700
Data Index: 1338264 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.8908. Min Act: -0.1700
Data Index: 6720597 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.8908. Min Act: -0.1700
Data Index: 3560893 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.8908. Min Act: -0.1700
Data Index: 1831994 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.8595. Min Act: -0.1700
Data Index: 666593 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.7970. Min Act: -0.1700
Data Index: 676994 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.7345. Min Act: -0.1700
Data Index: 5977268 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.7658. Min Act: -0.1700
Data Index: 5996947 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.6720. Min Act: -0.1700
Data Index: 4723138 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.7033. Min Act: -0.1700
Data Index: 1502060 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.7033. Min Act: -0.1700
Data Index: 6876019 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.6720. Min Act: -0.1700
Data Index: 3757162 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.6720. Min Act: -0.1700
Data Index: 8584449 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.6720. Min Act: -0.1700
Data Index: 5246496 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.6720. Min Act: -0.1700
Data Index: 7370147 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.6720. Min Act: -0.1700
Data Index: 5843662 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.6720. Min Act: -0.1700
Data Index: 2544 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.6720. Min Act: -0.1700
Data Index: 2183784 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.6720. Min Act: -0.1700
Data Index: 6659497 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9533. Min Range: -4.9533
Max Act: 4.6408. Min Act: -0.1700
Data Index: 2340891 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19