Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3705 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.8155. Min Act: -0.1700
Data Index: 1094975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7842. Min Act: -0.1700
Data Index: 2355593 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7842. Min Act: -0.1700
Data Index: 1289464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7530. Min Act: -0.1700
Data Index: 2285520 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7530. Min Act: -0.1700
Data Index: 8815973 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7217. Min Act: -0.1700
Data Index: 3871651 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7530. Min Act: -0.1700
Data Index: 5106556 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7217. Min Act: -0.1700
Data Index: 6209074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7217. Min Act: -0.1700
Data Index: 6424090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7217. Min Act: -0.1700
Data Index: 1875193 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7217. Min Act: -0.1700
Data Index: 2481624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7217. Min Act: -0.1700
Data Index: 4163063 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.6591. Min Act: -0.1700
Data Index: 236852 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.6904. Min Act: -0.1700
Data Index: 3030368 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.6904. Min Act: -0.1700
Data Index: 1382071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.6904. Min Act: -0.1700
Data Index: 3386532 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.6591. Min Act: -0.1700
Data Index: 3749811 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.6591. Min Act: -0.1700
Data Index: 6530252 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.6904. Min Act: -0.1700
Data Index: 8022151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.6904. Min Act: -0.1700
Data Index: 1251090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19