Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1505 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1470. Min Range: -3.1470
Max Act: 3.0998. Min Act: -0.1700
Data Index: 4437903 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1470. Min Range: -3.1470
Max Act: 3.1470. Min Act: -0.1700
Data Index: 6649183 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1470. Min Range: -3.1470
Max Act: 3.0840. Min Act: -0.1700
Data Index: 2551974 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1470. Min Range: -3.1470
Max Act: 3.0682. Min Act: -0.1700
Data Index: 600742 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1470. Min Range: -3.1470
Max Act: 3.0525. Min Act: -0.1700
Data Index: 7922646 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1470. Min Range: -3.1470
Max Act: 3.0682. Min Act: -0.1700
Data Index: 4534473 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1470. Min Range: -3.1470
Max Act: 3.0367. Min Act: -0.1700
Data Index: 5951349 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9893. Min Act: -0.1700
Data Index: 5202250 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1470. Min Range: -3.1470
Max Act: 3.0051. Min Act: -0.1700
Data Index: 8261596 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9893. Min Act: -0.1700
Data Index: 2870406 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9893. Min Act: -0.1700
Data Index: 1420104 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9893. Min Act: -0.1700
Data Index: 1825640 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9576. Min Act: -0.1700
Data Index: 918886 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9735. Min Act: -0.1700
Data Index: 1209053 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9735. Min Act: -0.1700
Data Index: 2067960 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9418. Min Act: -0.1700
Data Index: 3553086 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.8943. Min Act: -0.1700
Data Index: 658777 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9576. Min Act: -0.1700
Data Index: 7802480 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9418. Min Act: -0.1700
Data Index: 6410429 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1470. Min Range: -3.1470
Max Act: 2.9260. Min Act: -0.1700
Data Index: 5550918 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19