Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1439 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.4995. Min Act: -0.1700
Data Index: 6902816 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.4907. Min Act: -0.1700
Data Index: 6372552 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.4467. Min Act: -0.1700
Data Index: 7419672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.4379. Min Act: -0.1700
Data Index: 6579404 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.4379. Min Act: -0.1700
Data Index: 267805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.4291. Min Act: -0.1700
Data Index: 6135991 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.4027. Min Act: -0.1700
Data Index: 1546985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.4203. Min Act: -0.1700
Data Index: 1570667 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.4115. Min Act: -0.1700
Data Index: 3791486 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3939. Min Act: -0.1700
Data Index: 958570 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3851. Min Act: -0.1700
Data Index: 2530519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3851. Min Act: -0.1700
Data Index: 1669848 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3763. Min Act: -0.1700
Data Index: 5565878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3763. Min Act: -0.1700
Data Index: 5949960 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3675. Min Act: -0.1700
Data Index: 4318979 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3675. Min Act: -0.1700
Data Index: 7537458 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3675. Min Act: -0.1700
Data Index: 8067143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3675. Min Act: -0.1700
Data Index: 1614134 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3586. Min Act: -0.1700
Data Index: 6417110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4995. Min Range: -1.4995
Max Act: 1.3498. Min Act: -0.1700
Data Index: 1370524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19