Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.3930. Min Act: -0.1700
Data Index: 4799974 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.3930. Min Act: -0.1700
Data Index: 7033022 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.3930. Min Act: -0.1700
Data Index: 6086818 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.3618. Min Act: -0.1700
Data Index: 1387320 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.3618. Min Act: -0.1700
Data Index: 7003028 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.3618. Min Act: -0.1699
Data Index: 8348060 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.3305. Min Act: -0.1700
Data Index: 1748354 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2992. Min Act: -0.1700
Data Index: 3895803 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2992. Min Act: -0.1700
Data Index: 6860493 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2680. Min Act: -0.1700
Data Index: 5051396 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2680. Min Act: -0.1700
Data Index: 7646073 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2680. Min Act: -0.1700
Data Index: 255833 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2680. Min Act: -0.1699
Data Index: 2358388 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2680. Min Act: -0.1700
Data Index: 1748353 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2680. Min Act: -0.1700
Data Index: 8311937 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2367. Min Act: -0.1700
Data Index: 7296902 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2055. Min Act: -0.1700
Data Index: 29348 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2367. Min Act: -0.1700
Data Index: 980308 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2367. Min Act: -0.1700
Data Index: 5770633 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3930. Min Range: -4.3930
Max Act: 4.2367. Min Act: -0.1700
Data Index: 3002326 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19