Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 208 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4741. Min Act: -0.1700
Data Index: 889075 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4741. Min Act: -0.1700
Data Index: 76353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4741. Min Act: -0.1700
Data Index: 8618031 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4741. Min Act: -0.1700
Data Index: 3320171 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4741. Min Act: -0.1700
Data Index: 4925850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4741. Min Act: -0.1700
Data Index: 5199342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4741. Min Act: -0.1700
Data Index: 2887157 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 5951850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 8238065 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 8173803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 7402946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4741. Min Act: -0.1700
Data Index: 7280815 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 6543342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 177513 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 1660931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 3536010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 1084366 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 1007430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4427. Min Act: -0.1700
Data Index: 965976 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4741. Min Range: -3.4741
Max Act: 3.4114. Min Act: -0.1700
Data Index: 3104893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19