Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1058 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2057. Min Range: -4.2057
Max Act: 4.2057. Min Act: -0.1700
Data Index: 6497449 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2057. Min Range: -4.2057
Max Act: 4.1432. Min Act: -0.1700
Data Index: 822351 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2057. Min Range: -4.2057
Max Act: 4.1744. Min Act: -0.1700
Data Index: 3851881 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2057. Min Range: -4.2057
Max Act: 4.1119. Min Act: -0.1700
Data Index: 3667728 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.9869. Min Act: -0.1700
Data Index: 2561582 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2057. Min Range: -4.2057
Max Act: 4.0182. Min Act: -0.1700
Data Index: 990397 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.9244. Min Act: -0.1700
Data Index: 1566261 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.9244. Min Act: -0.1700
Data Index: 2285646 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8931. Min Act: -0.1700
Data Index: 689890 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.9244. Min Act: -0.1700
Data Index: 1954719 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8931. Min Act: -0.1700
Data Index: 1684320 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8931. Min Act: -0.1700
Data Index: 462739 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8618. Min Act: -0.1700
Data Index: 6250371 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8931. Min Act: -0.1700
Data Index: 1370363 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8306. Min Act: -0.1700
Data Index: 2724413 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8618. Min Act: -0.1700
Data Index: 5754103 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8618. Min Act: -0.1700
Data Index: 6881013 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8618. Min Act: -0.1700
Data Index: 2047966 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8306. Min Act: -0.1700
Data Index: 1566260 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2057. Min Range: -4.2057
Max Act: 3.8306. Min Act: -0.1700
Data Index: 5087324 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19