Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1541 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.4441. Min Act: -0.1700
Data Index: 6655353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3952. Min Act: -0.1700
Data Index: 4956673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3788. Min Act: -0.1700
Data Index: 2545706 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3625. Min Act: -0.1700
Data Index: 5650097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3461. Min Act: -0.1700
Data Index: 6898728 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3625. Min Act: -0.1700
Data Index: 42280 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3461. Min Act: -0.1700
Data Index: 5843282 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3297. Min Act: -0.1700
Data Index: 4815299 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3297. Min Act: -0.1700
Data Index: 7846038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3461. Min Act: -0.1700
Data Index: 4014868 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3297. Min Act: -0.1700
Data Index: 4676613 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3133. Min Act: -0.1700
Data Index: 5234179 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3133. Min Act: -0.1700
Data Index: 6580787 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3133. Min Act: -0.1700
Data Index: 2803720 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3133. Min Act: -0.1700
Data Index: 4702657 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3297. Min Act: -0.1700
Data Index: 2353491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.2968. Min Act: -0.1700
Data Index: 2028357 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.2968. Min Act: -0.1700
Data Index: 5276184 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.3133. Min Act: -0.1700
Data Index: 4905758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4441. Min Range: -2.4441
Max Act: 2.2804. Min Act: -0.1700
Data Index: 3891675 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19