Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1085 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.5921. Min Act: -0.1700
Data Index: 1183125 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.5296. Min Act: -0.1700
Data Index: 94562 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.5296. Min Act: -0.1700
Data Index: 1103477 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.5296. Min Act: -0.1700
Data Index: 4751663 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.5296. Min Act: -0.1700
Data Index: 4948263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.5296. Min Act: -0.1700
Data Index: 2313293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 2232661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 2867028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4671. Min Act: -0.1700
Data Index: 8530986 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 8297949 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 7209467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 915331 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 6374745 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 1316053 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 696132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 4667017 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 4266480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4671. Min Act: -0.1700
Data Index: 3743209 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 3525425 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5921. Min Range: -4.5921
Max Act: 4.4984. Min Act: -0.1700
Data Index: 3177275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19