Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4432 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.5658. Min Act: -0.1696
Data Index: 4052826 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.5483. Min Act: -0.1700
Data Index: 1749922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4869. Min Act: -0.1700
Data Index: 5609074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4781. Min Act: -0.1700
Data Index: 7767690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4693. Min Act: -0.1700
Data Index: 1656993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4693. Min Act: -0.1700
Data Index: 1484750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4605. Min Act: -0.1700
Data Index: 748908 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4517. Min Act: -0.1700
Data Index: 6827631 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4517. Min Act: -0.1700
Data Index: 5172468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4429. Min Act: -0.1700
Data Index: 8597390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4517. Min Act: -0.1700
Data Index: 5681071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4429. Min Act: -0.1700
Data Index: 3393120 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4341. Min Act: -0.1700
Data Index: 505055 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4341. Min Act: -0.1696
Data Index: 2330847 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4341. Min Act: -0.1700
Data Index: 1476810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4341. Min Act: -0.1696
Data Index: 5999079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4253. Min Act: -0.1699
Data Index: 6939899 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4165. Min Act: -0.1698
Data Index: 3724845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4165. Min Act: -0.1700
Data Index: 2996225 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5658. Min Range: -1.5658
Max Act: 1.4165. Min Act: -0.1700
Data Index: 2134668 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19