Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 123 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.6095. Min Act: -0.1700
Data Index: 3143024 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.3907. Min Act: -0.1699
Data Index: 195173 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.3595. Min Act: -0.1700
Data Index: 6590508 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.2970. Min Act: -0.1700
Data Index: 4165854 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.1407. Min Act: -0.1700
Data Index: 4916600 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.1407. Min Act: -0.1700
Data Index: 4936007 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.1407. Min Act: -0.1700
Data Index: 1647997 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.1407. Min Act: -0.1700
Data Index: 2918356 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.1407. Min Act: -0.1700
Data Index: 1281946 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.1407. Min Act: -0.1700
Data Index: 6172146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.1095. Min Act: -0.1699
Data Index: 5000623 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.0782. Min Act: -0.1700
Data Index: 8585435 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.0782. Min Act: -0.1700
Data Index: 4750430 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.0782. Min Act: -0.1700
Data Index: 6306373 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.0470. Min Act: -0.1700
Data Index: 6288598 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.0157. Min Act: -0.1700
Data Index: 5486956 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.0157. Min Act: -0.1691
Data Index: 7937288 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.0157. Min Act: -0.1697
Data Index: 5870404 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.0157. Min Act: -0.1700
Data Index: 6061119 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6095. Min Range: -6.6095
Max Act: 6.0157. Min Act: -0.1700
Data Index: 5063519 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19