Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 299 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.1130. Min Act: -0.1696
Data Index: 3127717 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0955. Min Act: -0.1698
Data Index: 2443202 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0780. Min Act: -0.1700
Data Index: 4915060 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0431. Min Act: -0.1700
Data Index: 5914821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0605. Min Act: -0.1700
Data Index: 2668859 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0605. Min Act: -0.1694
Data Index: 7106600 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0780. Min Act: -0.1700
Data Index: 6021876 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0431. Min Act: -0.1700
Data Index: 272921 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0256. Min Act: -0.1696
Data Index: 272926 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0431. Min Act: -0.1696
Data Index: 4830508 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0605. Min Act: -0.1696
Data Index: 4953307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0256. Min Act: -0.1700
Data Index: 3777522 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0256. Min Act: -0.1694
Data Index: 3949022 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0431. Min Act: -0.1698
Data Index: 174055 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0605. Min Act: -0.1700
Data Index: 2137148 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1130. Min Range: -1.1130
Max Act: 0.9909. Min Act: -0.1700
Data Index: 3713127 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0083. Min Act: -0.1700
Data Index: 5312115 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0083. Min Act: -0.1700
Data Index: 2189887 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1130. Min Range: -1.1130
Max Act: 1.0083. Min Act: -0.1699
Data Index: 6343140 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1130. Min Range: -1.1130
Max Act: 0.9909. Min Act: -0.1700
Data Index: 7221590 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19