Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2972. Min Range: -6.2972
Max Act: 6.2972. Min Act: -0.1700
Data Index: 333012 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.9535. Min Act: -0.1700
Data Index: 8470626 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.9535. Min Act: -0.1700
Data Index: 4214642 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.9222. Min Act: -0.1700
Data Index: 4107531 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.8597. Min Act: -0.1700
Data Index: 3041293 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.8597. Min Act: -0.1700
Data Index: 4214636 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.7972. Min Act: -0.1700
Data Index: 1245995 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.7972. Min Act: -0.1700
Data Index: 6075865 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.7660. Min Act: -0.1700
Data Index: 3044636 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.7660. Min Act: -0.1700
Data Index: 3202091 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.7347. Min Act: -0.1700
Data Index: 1674044 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.7347. Min Act: -0.1700
Data Index: 8014994 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.7347. Min Act: -0.1700
Data Index: 6391013 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.7035. Min Act: -0.1700
Data Index: 8253787 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.6722. Min Act: -0.1700
Data Index: 5026365 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.7035. Min Act: -0.1700
Data Index: 4335079 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.6410. Min Act: -0.1700
Data Index: 7907572 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.6722. Min Act: -0.1700
Data Index: 4107525 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.6722. Min Act: -0.1700
Data Index: 6347631 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2972. Min Range: -6.2972
Max Act: 5.6410. Min Act: -0.1700
Data Index: 4421115 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19