Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.5635. Min Act: -0.1700
Data Index: 4481379 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.5373. Min Act: -0.1700
Data Index: 4731829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.5197. Min Act: -0.1700
Data Index: 8372843 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.5197. Min Act: -0.1700
Data Index: 1971185 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.5197. Min Act: -0.1699
Data Index: 1535539 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.5022. Min Act: -0.1698
Data Index: 4776236 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4934. Min Act: -0.1698
Data Index: 2171613 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.5110. Min Act: -0.1700
Data Index: 8205302 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.5022. Min Act: -0.1700
Data Index: 2724752 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4934. Min Act: -0.1700
Data Index: 6776590 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.5022. Min Act: -0.1700
Data Index: 2589418 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4934. Min Act: -0.1700
Data Index: 4385189 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4846. Min Act: -0.1700
Data Index: 3929916 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4846. Min Act: -0.1700
Data Index: 6182719 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4758. Min Act: -0.1700
Data Index: 1029351 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4758. Min Act: -0.1677
Data Index: 4769251 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4758. Min Act: -0.1700
Data Index: 1398948 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4758. Min Act: -0.1700
Data Index: 5870842 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4758. Min Act: -0.1700
Data Index: 2869360 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5635. Min Range: -1.5635
Max Act: 1.4758. Min Act: -0.1700
Data Index: 3113450 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19