Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0698. Min Range: -2.0698
Max Act: 2.0698. Min Act: -0.1700
Data Index: 2400457 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.9006. Min Act: -0.1700
Data Index: 618115 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.9091. Min Act: -0.1684
Data Index: 998834 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8921. Min Act: -0.1700
Data Index: 2975169 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8921. Min Act: -0.1613
Data Index: 4505228 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8921. Min Act: -0.1696
Data Index: 6407114 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8921. Min Act: -0.1700
Data Index: 4560716 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8750. Min Act: -0.1700
Data Index: 6325642 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8664. Min Act: -0.1700
Data Index: 3329047 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8664. Min Act: -0.1700
Data Index: 4473964 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8579. Min Act: -0.1700
Data Index: 1286722 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8579. Min Act: -0.1700
Data Index: 3928331 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8407. Min Act: -0.1700
Data Index: 7281979 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8407. Min Act: -0.1700
Data Index: 7536786 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8493. Min Act: -0.1700
Data Index: 1760298 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8407. Min Act: -0.1698
Data Index: 2230548 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8236. Min Act: -0.1700
Data Index: 1068855 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8493. Min Act: -0.1699
Data Index: 3948865 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8322. Min Act: -0.1700
Data Index: 459603 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0698. Min Range: -2.0698
Max Act: 1.8322. Min Act: -0.1690
Data Index: 3399138 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19