Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1615 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5378. Min Range: -8.5378
Max Act: 8.5378. Min Act: -0.1700
Data Index: 6287138 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5378. Min Range: -8.5378
Max Act: 8.4753. Min Act: -0.1700
Data Index: 3759409 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5378. Min Range: -8.5378
Max Act: 8.1628. Min Act: -0.1700
Data Index: 2140231 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5378. Min Range: -8.5378
Max Act: 8.1003. Min Act: -0.1700
Data Index: 1481179 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5378. Min Range: -8.5378
Max Act: 8.0378. Min Act: -0.1700
Data Index: 4890111 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5378. Min Range: -8.5378
Max Act: 8.0378. Min Act: -0.1700
Data Index: 807134 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5378. Min Range: -8.5378
Max Act: 8.0378. Min Act: -0.1700
Data Index: 360006 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.9753. Min Act: -0.1700
Data Index: 8794048 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.9753. Min Act: -0.1700
Data Index: 8318719 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.9753. Min Act: -0.1700
Data Index: 5630787 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.9128. Min Act: -0.1700
Data Index: 6359166 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.8503. Min Act: -0.1700
Data Index: 4220285 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.8503. Min Act: -0.1700
Data Index: 7375847 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.7878. Min Act: -0.1700
Data Index: 5829516 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.8191. Min Act: -0.1700
Data Index: 3696561 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.7878. Min Act: -0.1700
Data Index: 1570645 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.7566. Min Act: -0.1700
Data Index: 334749 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.7253. Min Act: -0.1700
Data Index: 7869137 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.7253. Min Act: -0.1700
Data Index: 2972747 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5378. Min Range: -8.5378
Max Act: 7.7253. Min Act: -0.1700
Data Index: 2884481 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19