Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2888 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.2019. Min Act: -0.1700
Data Index: 5593164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.2019. Min Act: -0.1700
Data Index: 7999112 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1520. Min Act: -0.1700
Data Index: 3452668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1520. Min Act: -0.1700
Data Index: 2049529 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1520. Min Act: -0.1700
Data Index: 6285688 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1354. Min Act: -0.1700
Data Index: 6775745 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1687. Min Act: -0.1700
Data Index: 7242382 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1520. Min Act: -0.1700
Data Index: 8451110 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1687. Min Act: -0.1700
Data Index: 7883204 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1354. Min Act: -0.1700
Data Index: 8078640 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1187. Min Act: -0.1700
Data Index: 5105586 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1187. Min Act: -0.1700
Data Index: 2854192 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1354. Min Act: -0.1700
Data Index: 8089212 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1354. Min Act: -0.1700
Data Index: 7518361 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1354. Min Act: -0.1700
Data Index: 7288423 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1354. Min Act: -0.1700
Data Index: 5597196 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1187. Min Act: -0.1700
Data Index: 2471620 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1187. Min Act: -0.1700
Data Index: 2769618 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1187. Min Act: -0.1700
Data Index: 2777360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2019. Min Range: -2.2019
Max Act: 2.1187. Min Act: -0.1700
Data Index: 1965162 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19