Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.3520. Min Act: -0.1700
Data Index: 8751692 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.3520. Min Act: -0.1700
Data Index: 5292888 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2895. Min Act: -0.1700
Data Index: 2223233 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2895. Min Act: -0.1700
Data Index: 2063618 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2895. Min Act: -0.1700
Data Index: 2964655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1957. Min Act: -0.1700
Data Index: 4116331 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 3048695 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 2715169 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 2714245 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 5646928 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 4893934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 4427119 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1957. Min Act: -0.1700
Data Index: 999121 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1957. Min Act: -0.1700
Data Index: 5835638 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1957. Min Act: -0.1700
Data Index: 556169 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1957. Min Act: -0.1700
Data Index: 6329876 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 1206579 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1957. Min Act: -0.1700
Data Index: 6937097 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1957. Min Act: -0.1700
Data Index: 1356589 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1957. Min Act: -0.1700
Data Index: 4326349 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19