Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 148 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5741. Min Act: -0.1700
Data Index: 1611606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5547. Min Act: -0.1700
Data Index: 2715356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5394. Min Act: -0.1700
Data Index: 286466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5432. Min Act: -0.1700
Data Index: 4559924 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5355. Min Act: -0.1700
Data Index: 2616180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5355. Min Act: -0.1700
Data Index: 1385680 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5355. Min Act: -0.1700
Data Index: 1914777 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5279. Min Act: -0.1700
Data Index: 5253027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5241. Min Act: -0.1700
Data Index: 8220964 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5127. Min Act: -0.1700
Data Index: 7834767 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5127. Min Act: -0.1700
Data Index: 8038275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.5014. Min Act: -0.1700
Data Index: 6787271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.4977. Min Act: -0.1700
Data Index: 5106224 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.4939. Min Act: -0.1700
Data Index: 7816628 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.4827. Min Act: -0.1700
Data Index: 4287690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.4716. Min Act: -0.1700
Data Index: 8417010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.4606. Min Act: -0.1700
Data Index: 1209398 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.4606. Min Act: -0.1700
Data Index: 6027377 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.4642. Min Act: -0.1700
Data Index: 4923170 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5741. Min Range: -0.5741
Max Act: 0.4642. Min Act: -0.1700
Data Index: 5406429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19