Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2082 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.1272. Min Act: -0.1700
Data Index: 6910386 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.1585. Min Act: -0.1700
Data Index: 218031 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.1585. Min Act: -0.1700
Data Index: 1042829 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.1272. Min Act: -0.1700
Data Index: 6415472 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0960. Min Act: -0.1700
Data Index: 4146255 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0960. Min Act: -0.1700
Data Index: 8481750 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0647. Min Act: -0.1700
Data Index: 5942053 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0647. Min Act: -0.1700
Data Index: 6852457 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0335. Min Act: -0.1700
Data Index: 5853571 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0647. Min Act: -0.1700
Data Index: 7993306 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0022. Min Act: -0.1700
Data Index: 7653928 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0022. Min Act: -0.1700
Data Index: 8594477 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0335. Min Act: -0.1700
Data Index: 5691593 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0335. Min Act: -0.1700
Data Index: 4613680 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1585. Min Range: -5.1585
Max Act: 5.0022. Min Act: -0.1700
Data Index: 6852456 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1585. Min Range: -5.1585
Max Act: 4.9397. Min Act: -0.1700
Data Index: 5405660 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1585. Min Range: -5.1585
Max Act: 4.9710. Min Act: -0.1700
Data Index: 5190865 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1585. Min Range: -5.1585
Max Act: 4.9710. Min Act: -0.1700
Data Index: 1472456 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1585. Min Range: -5.1585
Max Act: 4.9710. Min Act: -0.1700
Data Index: 5858893 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1585. Min Range: -5.1585
Max Act: 4.9397. Min Act: -0.1700
Data Index: 4475997 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19