Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2399 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.1364. Min Act: -0.1700
Data Index: 232894 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0738. Min Act: -0.1700
Data Index: 6716182 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0426. Min Act: -0.1700
Data Index: 1451648 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0426. Min Act: -0.1700
Data Index: 4608078 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0426. Min Act: -0.1700
Data Index: 3408663 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0426. Min Act: -0.1700
Data Index: 7434667 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0426. Min Act: -0.1700
Data Index: 5570242 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0113. Min Act: -0.1700
Data Index: 2617465 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0113. Min Act: -0.1700
Data Index: 254726 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0113. Min Act: -0.1700
Data Index: 396680 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0113. Min Act: -0.1700
Data Index: 6942954 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1364. Min Range: -4.1364
Max Act: 4.0113. Min Act: -0.1700
Data Index: 6433819 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1364. Min Range: -4.1364
Max Act: 3.9801. Min Act: -0.1700
Data Index: 3934403 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1364. Min Range: -4.1364
Max Act: 3.9801. Min Act: -0.1700
Data Index: 3408664 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1364. Min Range: -4.1364
Max Act: 3.9801. Min Act: -0.1700
Data Index: 1620387 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1364. Min Range: -4.1364
Max Act: 3.9801. Min Act: -0.1700
Data Index: 4084877 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1364. Min Range: -4.1364
Max Act: 3.9801. Min Act: -0.1700
Data Index: 4280043 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1364. Min Range: -4.1364
Max Act: 3.9801. Min Act: -0.1700
Data Index: 4515967 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1364. Min Range: -4.1364
Max Act: 3.9801. Min Act: -0.1700
Data Index: 5989489 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1364. Min Range: -4.1364
Max Act: 3.9801. Min Act: -0.1700
Data Index: 472822 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19