Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2679 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1794. Min Range: -7.1794
Max Act: 7.1794. Min Act: -0.1700
Data Index: 2466078 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1794. Min Range: -7.1794
Max Act: 7.1794. Min Act: -0.1700
Data Index: 4236885 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1794. Min Range: -7.1794
Max Act: 7.1169. Min Act: -0.1700
Data Index: 6496369 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1794. Min Range: -7.1794
Max Act: 7.1169. Min Act: -0.1700
Data Index: 7247494 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1794. Min Range: -7.1794
Max Act: 7.0544. Min Act: -0.1700
Data Index: 1952222 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1794. Min Range: -7.1794
Max Act: 7.0856. Min Act: -0.1700
Data Index: 6570815 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1794. Min Range: -7.1794
Max Act: 7.0544. Min Act: -0.1700
Data Index: 5666211 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.9919. Min Act: -0.1700
Data Index: 4598149 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.3044. Min Act: -0.1700
Data Index: 481498 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.9294. Min Act: -0.1700
Data Index: 1924167 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.9294. Min Act: -0.1700
Data Index: 1926842 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.9294. Min Act: -0.1700
Data Index: 6463338 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.9294. Min Act: -0.1700
Data Index: 6730265 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.9294. Min Act: -0.1700
Data Index: 749951 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.8669. Min Act: -0.1700
Data Index: 7396418 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.8981. Min Act: -0.1700
Data Index: 4131847 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.6481. Min Act: -0.1700
Data Index: 57197 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.8669. Min Act: -0.1700
Data Index: 1724848 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.8981. Min Act: -0.1700
Data Index: 998035 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1794. Min Range: -7.1794
Max Act: 6.8044. Min Act: -0.1700
Data Index: 6280484 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19