Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3109 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.6389. Min Act: -0.1700
Data Index: 4135513 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.6233. Min Act: -0.1700
Data Index: 545202 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.5920. Min Act: -0.1700
Data Index: 3163215 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.6076. Min Act: -0.1700
Data Index: 13420 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.6076. Min Act: -0.1700
Data Index: 2398388 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.5450. Min Act: -0.1700
Data Index: 435040 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.5450. Min Act: -0.1700
Data Index: 4328045 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.5293. Min Act: -0.1700
Data Index: 3163213 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4824. Min Act: -0.1700
Data Index: 6206829 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4980. Min Act: -0.1700
Data Index: 900832 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.5137. Min Act: -0.1700
Data Index: 3310268 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4980. Min Act: -0.1700
Data Index: 4135512 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4667. Min Act: -0.1700
Data Index: 8284506 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4667. Min Act: -0.1700
Data Index: 2819847 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4510. Min Act: -0.1700
Data Index: 296298 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4510. Min Act: -0.1700
Data Index: 8410458 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4510. Min Act: -0.1700
Data Index: 7406427 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4354. Min Act: -0.1700
Data Index: 4244993 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4197. Min Act: -0.1700
Data Index: 7213685 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6389. Min Range: -3.6389
Max Act: 3.4354. Min Act: -0.1700
Data Index: 3498124 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19