Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.1883. Min Act: -0.1700
Data Index: 7810814 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.1726. Min Act: -0.1700
Data Index: 4337520 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.1569. Min Act: -0.1700
Data Index: 3861943 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.1096. Min Act: -0.1700
Data Index: 8583341 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.1254. Min Act: -0.1700
Data Index: 7079908 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0939. Min Act: -0.1700
Data Index: 1836605 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0939. Min Act: -0.1700
Data Index: 5644492 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0939. Min Act: -0.1700
Data Index: 3821423 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0623. Min Act: -0.1700
Data Index: 6919954 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0465. Min Act: -0.1700
Data Index: 4556310 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0465. Min Act: -0.1700
Data Index: 1610396 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0623. Min Act: -0.1700
Data Index: 1636520 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0623. Min Act: -0.1700
Data Index: 2099001 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0623. Min Act: -0.1700
Data Index: 5831017 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0465. Min Act: -0.1700
Data Index: 3409353 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0150. Min Act: -0.1700
Data Index: 3838588 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0307. Min Act: -0.1700
Data Index: 7042878 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0465. Min Act: -0.1700
Data Index: 8457559 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0150. Min Act: -0.1700
Data Index: 3097236 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1883. Min Range: -3.1883
Max Act: 3.0150. Min Act: -0.1700
Data Index: 3543765 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19