Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1856. Min Range: -3.1856
Max Act: 3.1856. Min Act: -0.1700
Data Index: 5725239 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1856. Min Range: -3.1856
Max Act: 3.1541. Min Act: -0.1700
Data Index: 5725241 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1856. Min Range: -3.1856
Max Act: 3.0280. Min Act: -0.1700
Data Index: 345611 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9964. Min Act: -0.1700
Data Index: 3542024 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9806. Min Act: -0.1700
Data Index: 880453 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9964. Min Act: -0.1700
Data Index: 1549805 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9964. Min Act: -0.1700
Data Index: 6618058 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9648. Min Act: -0.1700
Data Index: 1475149 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9489. Min Act: -0.1700
Data Index: 269309 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9489. Min Act: -0.1700
Data Index: 5198355 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9648. Min Act: -0.1700
Data Index: 8795318 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9331. Min Act: -0.1700
Data Index: 1412058 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9489. Min Act: -0.1700
Data Index: 7475033 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9173. Min Act: -0.1700
Data Index: 3984010 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9173. Min Act: -0.1700
Data Index: 3041336 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9173. Min Act: -0.1700
Data Index: 7236221 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9014. Min Act: -0.1700
Data Index: 3066665 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9014. Min Act: -0.1700
Data Index: 7628944 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.8855. Min Act: -0.1700
Data Index: 7321368 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1856. Min Range: -3.1856
Max Act: 2.9014. Min Act: -0.1700
Data Index: 6650402 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19