Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2510 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0126. Min Range: -4.0126
Max Act: 4.0126. Min Act: -0.1700
Data Index: 3643439 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.9188. Min Act: -0.1700
Data Index: 3238021 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.8875. Min Act: -0.1700
Data Index: 2877317 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.9188. Min Act: -0.1700
Data Index: 3180720 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.8562. Min Act: -0.1700
Data Index: 3592751 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.8250. Min Act: -0.1700
Data Index: 6124738 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.8250. Min Act: -0.1700
Data Index: 4837144 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7937. Min Act: -0.1700
Data Index: 6915820 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7624. Min Act: -0.1700
Data Index: 5085799 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7937. Min Act: -0.1700
Data Index: 5855958 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7937. Min Act: -0.1700
Data Index: 602653 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7937. Min Act: -0.1700
Data Index: 5103167 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7937. Min Act: -0.1700
Data Index: 6611750 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7624. Min Act: -0.1700
Data Index: 1401237 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7624. Min Act: -0.1700
Data Index: 5952540 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7311. Min Act: -0.1700
Data Index: 1433371 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7311. Min Act: -0.1700
Data Index: 3015568 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7311. Min Act: -0.1700
Data Index: 4904877 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7311. Min Act: -0.1700
Data Index: 3850740 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0126. Min Range: -4.0126
Max Act: 3.7311. Min Act: -0.1700
Data Index: 313514 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19