Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.3237. Min Act: -0.1700
Data Index: 6748955 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1987. Min Act: -0.1700
Data Index: 8686959 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.2300. Min Act: -0.1700
Data Index: 7977021 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.2300. Min Act: -0.1700
Data Index: 205845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1987. Min Act: -0.1700
Data Index: 3653958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1987. Min Act: -0.1700
Data Index: 4181479 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1987. Min Act: -0.1700
Data Index: 3537381 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1675. Min Act: -0.1700
Data Index: 4221816 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1362. Min Act: -0.1700
Data Index: 2823991 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1675. Min Act: -0.1700
Data Index: 5445681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1675. Min Act: -0.1700
Data Index: 5233871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1675. Min Act: -0.1700
Data Index: 7546598 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1675. Min Act: -0.1700
Data Index: 6770257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1675. Min Act: -0.1700
Data Index: 2604709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1362. Min Act: -0.1700
Data Index: 3965157 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1362. Min Act: -0.1700
Data Index: 7199333 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1362. Min Act: -0.1700
Data Index: 1931448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1050. Min Act: -0.1700
Data Index: 3598189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1362. Min Act: -0.1700
Data Index: 2890727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3237. Min Range: -5.3237
Max Act: 5.1362. Min Act: -0.1700
Data Index: 7980915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19