Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4933 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.5401. Min Act: -0.1700
Data Index: 5014850 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4915. Min Act: -0.1700
Data Index: 824113 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4915. Min Act: -0.1700
Data Index: 394252 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4753. Min Act: -0.1700
Data Index: 1649996 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4753. Min Act: -0.1700
Data Index: 5014849 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4428. Min Act: -0.1700
Data Index: 6440262 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4591. Min Act: -0.1700
Data Index: 8356505 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4428. Min Act: -0.1700
Data Index: 4750116 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4591. Min Act: -0.1700
Data Index: 2576540 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4265. Min Act: -0.1700
Data Index: 5512433 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4265. Min Act: -0.1700
Data Index: 4927840 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4265. Min Act: -0.1700
Data Index: 3780089 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4102. Min Act: -0.1700
Data Index: 6322471 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4102. Min Act: -0.1700
Data Index: 5059965 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4102. Min Act: -0.1700
Data Index: 5014858 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.4102. Min Act: -0.1700
Data Index: 5014855 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.3939. Min Act: -0.1700
Data Index: 8207326 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.3939. Min Act: -0.1700
Data Index: 3300347 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.3939. Min Act: -0.1700
Data Index: 822122 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5401. Min Range: -2.5401
Max Act: 2.3776. Min Act: -0.1700
Data Index: 983412 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19