Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.1489. Min Act: -0.1700
Data Index: 5741928 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.0552. Min Act: -0.1700
Data Index: 6261033 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9927. Min Act: -0.1700
Data Index: 2831919 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9614. Min Act: -0.1700
Data Index: 7698486 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9927. Min Act: -0.1700
Data Index: 1026304 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9927. Min Act: -0.1700
Data Index: 3569133 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9614. Min Act: -0.1700
Data Index: 4011029 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9614. Min Act: -0.1700
Data Index: 6367310 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9927. Min Act: -0.1700
Data Index: 6985250 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9614. Min Act: -0.1700
Data Index: 1146399 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9302. Min Act: -0.1700
Data Index: 607130 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9302. Min Act: -0.1700
Data Index: 7727119 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9302. Min Act: -0.1700
Data Index: 8397116 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9614. Min Act: -0.1700
Data Index: 7235262 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9302. Min Act: -0.1700
Data Index: 4158326 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9302. Min Act: -0.1700
Data Index: 8503059 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 301488 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 8286121 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 7346444 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 3387604 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19