Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2436 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.1462. Min Act: -0.1700
Data Index: 4449149 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.1462. Min Act: -0.1700
Data Index: 8021365 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.1147. Min Act: -0.1700
Data Index: 3704679 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0990. Min Act: -0.1700
Data Index: 2543532 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0990. Min Act: -0.1700
Data Index: 4346185 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.1147. Min Act: -0.1700
Data Index: 1420352 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0990. Min Act: -0.1700
Data Index: 3885378 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0832. Min Act: -0.1700
Data Index: 7088828 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0832. Min Act: -0.1700
Data Index: 3077608 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0832. Min Act: -0.1700
Data Index: 6165874 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0832. Min Act: -0.1700
Data Index: 3026607 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0832. Min Act: -0.1700
Data Index: 8563788 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0832. Min Act: -0.1700
Data Index: 6104460 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0832. Min Act: -0.1700
Data Index: 3457201 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0832. Min Act: -0.1700
Data Index: 7563179 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0832. Min Act: -0.1700
Data Index: 3265731 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0832. Min Act: -0.1700
Data Index: 7163516 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0674. Min Act: -0.1700
Data Index: 3926470 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0674. Min Act: -0.1700
Data Index: 2151154 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1462. Min Range: -3.1462
Max Act: 3.0674. Min Act: -0.1700
Data Index: 6920378 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19