Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0089. Min Range: -4.0089
Max Act: 4.0089. Min Act: -0.1700
Data Index: 3282700 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.8838. Min Act: -0.1700
Data Index: 4567777 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.8526. Min Act: -0.1700
Data Index: 4170008 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.8526. Min Act: -0.1700
Data Index: 5115604 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.8213. Min Act: -0.1700
Data Index: 7760639 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.8213. Min Act: -0.1700
Data Index: 3235670 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.8213. Min Act: -0.1700
Data Index: 6520937 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.7900. Min Act: -0.1700
Data Index: 6030221 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.7900. Min Act: -0.1700
Data Index: 2673667 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.7275. Min Act: -0.1700
Data Index: 1354926 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.8213. Min Act: -0.1700
Data Index: 7861359 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.7900. Min Act: -0.1700
Data Index: 879272 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.7587. Min Act: -0.1700
Data Index: 145746 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.7275. Min Act: -0.1700
Data Index: 3684278 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.6962. Min Act: -0.1700
Data Index: 5325161 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.7275. Min Act: -0.1700
Data Index: 6349202 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.7275. Min Act: -0.1700
Data Index: 1552646 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.6962. Min Act: -0.1700
Data Index: 7607675 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.6962. Min Act: -0.1700
Data Index: 5497883 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0089. Min Range: -4.0089
Max Act: 3.7275. Min Act: -0.1700
Data Index: 3008034 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19