Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.8674. Min Act: -0.1700
Data Index: 6445681 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.8361. Min Act: -0.1700
Data Index: 7401989 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.8049. Min Act: -0.1700
Data Index: 125580 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.7424. Min Act: -0.1700
Data Index: 355380 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.7424. Min Act: -0.1700
Data Index: 7407978 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.6799. Min Act: -0.1700
Data Index: 7154309 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.6486. Min Act: -0.1700
Data Index: 2587745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.6486. Min Act: -0.1700
Data Index: 1041006 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.6486. Min Act: -0.1700
Data Index: 211480 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.6486. Min Act: -0.1700
Data Index: 3201345 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.6174. Min Act: -0.1700
Data Index: 3268041 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5861. Min Act: -0.1700
Data Index: 1592109 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5549. Min Act: -0.1700
Data Index: 4508937 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5236. Min Act: -0.1700
Data Index: 4590213 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5236. Min Act: -0.1700
Data Index: 6229500 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5236. Min Act: -0.1700
Data Index: 8103743 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5236. Min Act: -0.1700
Data Index: 3758208 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.5236. Min Act: -0.1700
Data Index: 1266543 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.4924. Min Act: -0.1700
Data Index: 4590211 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8674. Min Range: -4.8674
Max Act: 4.4611. Min Act: -0.1700
Data Index: 1094120 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19