Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2952. Min Act: -0.1695
Data Index: 2882418 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2623. Min Act: -0.1700
Data Index: 2585826 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2127. Min Act: -0.1698
Data Index: 6651652 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2292. Min Act: -0.1700
Data Index: 3937131 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2292. Min Act: -0.1700
Data Index: 3707436 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2292. Min Act: -0.1700
Data Index: 221102 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2292. Min Act: -0.1700
Data Index: 2246798 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.1961. Min Act: -0.1700
Data Index: 2394227 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2127. Min Act: -0.1700
Data Index: 3882428 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2127. Min Act: -0.1700
Data Index: 7203777 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2127. Min Act: -0.1699
Data Index: 1115636 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.1961. Min Act: -0.1700
Data Index: 4269456 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.1795. Min Act: -0.1700
Data Index: 4650747 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.2127. Min Act: -0.1700
Data Index: 2882019 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.1795. Min Act: -0.1700
Data Index: 2052419 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.1628. Min Act: -0.1700
Data Index: 1617098 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.1795. Min Act: -0.1700
Data Index: 4421663 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.1628. Min Act: -0.1700
Data Index: 5018877 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.1628. Min Act: -0.1700
Data Index: 2585832 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2952. Min Range: -2.2952
Max Act: 2.1628. Min Act: -0.1700
Data Index: 2000997 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19