Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.2106. Min Act: -0.1688
Data Index: 4921622 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.1441. Min Act: -0.1700
Data Index: 5883675 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.1441. Min Act: -0.1700
Data Index: 5185522 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.1107. Min Act: -0.1698
Data Index: 6766790 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0772. Min Act: -0.1700
Data Index: 2931788 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0940. Min Act: -0.1700
Data Index: 2134100 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0940. Min Act: -0.1695
Data Index: 7674697 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0772. Min Act: -0.1691
Data Index: 3347905 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0772. Min Act: -0.1700
Data Index: 790158 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0772. Min Act: -0.1700
Data Index: 3071749 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0772. Min Act: -0.1700
Data Index: 8088157 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0772. Min Act: -0.1700
Data Index: 364368 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0772. Min Act: -0.1700
Data Index: 6502516 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0604. Min Act: -0.1700
Data Index: 8206906 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0604. Min Act: -0.1700
Data Index: 1630266 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0772. Min Act: -0.1698
Data Index: 5748230 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0772. Min Act: -0.1700
Data Index: 4446707 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0604. Min Act: -0.1700
Data Index: 8066976 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0604. Min Act: -0.1700
Data Index: 329178 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2106. Min Range: -2.2106
Max Act: 2.0604. Min Act: -0.1698
Data Index: 2310441 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19