Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.5546. Min Act: -0.1700
Data Index: 8396666 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.5546. Min Act: -0.1700
Data Index: 682050 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.4921. Min Act: -0.1700
Data Index: 4003381 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.4609. Min Act: -0.1700
Data Index: 133615 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.3984. Min Act: -0.1700
Data Index: 2585552 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.3671. Min Act: -0.1700
Data Index: 3040167 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.3984. Min Act: -0.1700
Data Index: 6092097 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.3984. Min Act: -0.1700
Data Index: 6991496 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.2734. Min Act: -0.1700
Data Index: 5715697 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.2421. Min Act: -0.1700
Data Index: 7742360 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.3984. Min Act: -0.1700
Data Index: 4524784 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.2109. Min Act: -0.1700
Data Index: 3009763 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.2734. Min Act: -0.1700
Data Index: 8518670 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.2421. Min Act: -0.1700
Data Index: 4514275 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.2421. Min Act: -0.1700
Data Index: 7894329 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.2109. Min Act: -0.1700
Data Index: 4850289 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.1796. Min Act: -0.1700
Data Index: 7091908 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.2109. Min Act: -0.1700
Data Index: 1987450 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.2109. Min Act: -0.1700
Data Index: 4406653 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5546. Min Range: -7.5546
Max Act: 7.1484. Min Act: -0.1700
Data Index: 4838026 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19