Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1327 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1133. Min Range: -5.1133
Max Act: 5.1133. Min Act: -0.1700
Data Index: 5767472 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1133. Min Range: -5.1133
Max Act: 5.0821. Min Act: -0.1700
Data Index: 7338873 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1133. Min Range: -5.1133
Max Act: 5.0196. Min Act: -0.1700
Data Index: 8229419 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.9571. Min Act: -0.1700
Data Index: 2456734 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.9258. Min Act: -0.1700
Data Index: 2347949 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.8946. Min Act: -0.1700
Data Index: 7719839 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.8633. Min Act: -0.1700
Data Index: 5395696 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.8321. Min Act: -0.1700
Data Index: 2015028 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.7696. Min Act: -0.1700
Data Index: 6685588 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.8008. Min Act: -0.1700
Data Index: 2196465 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.7696. Min Act: -0.1700
Data Index: 1905129 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.7696. Min Act: -0.1700
Data Index: 5767463 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.7383. Min Act: -0.1700
Data Index: 2021805 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.7383. Min Act: -0.1700
Data Index: 5839617 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.7071. Min Act: -0.1700
Data Index: 6700431 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.7383. Min Act: -0.1700
Data Index: 2009982 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.7071. Min Act: -0.1700
Data Index: 4314837 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.7071. Min Act: -0.1700
Data Index: 772892 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.6758. Min Act: -0.1700
Data Index: 5013754 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1133. Min Range: -5.1133
Max Act: 4.6758. Min Act: -0.1700
Data Index: 4990331 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19