Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4190 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2468. Min Range: -4.2468
Max Act: 4.2468. Min Act: -0.1700
Data Index: 5948909 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2468. Min Range: -4.2468
Max Act: 4.1530. Min Act: -0.1700
Data Index: 1843788 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2468. Min Range: -4.2468
Max Act: 4.1530. Min Act: -0.1700
Data Index: 419356 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2468. Min Range: -4.2468
Max Act: 4.1843. Min Act: -0.1700
Data Index: 4566526 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2468. Min Range: -4.2468
Max Act: 4.1218. Min Act: -0.1700
Data Index: 2320645 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2468. Min Range: -4.2468
Max Act: 4.1218. Min Act: -0.1700
Data Index: 6044860 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2468. Min Range: -4.2468
Max Act: 4.0905. Min Act: -0.1700
Data Index: 6732928 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2468. Min Range: -4.2468
Max Act: 4.0280. Min Act: -0.1700
Data Index: 3364570 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9967. Min Act: -0.1700
Data Index: 3259419 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9655. Min Act: -0.1700
Data Index: 4409461 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9655. Min Act: -0.1700
Data Index: 2833752 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9655. Min Act: -0.1700
Data Index: 8724608 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9342. Min Act: -0.1700
Data Index: 788545 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9029. Min Act: -0.1700
Data Index: 2845858 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9342. Min Act: -0.1700
Data Index: 5211753 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9029. Min Act: -0.1700
Data Index: 8669581 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9029. Min Act: -0.1700
Data Index: 3500323 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9029. Min Act: -0.1700
Data Index: 7044076 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.9029. Min Act: -0.1700
Data Index: 4684834 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2468. Min Range: -4.2468
Max Act: 3.8717. Min Act: -0.1700
Data Index: 4373128 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19