Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2385 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.5583. Min Act: -0.1698
Data Index: 765804 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.5408. Min Act: -0.1700
Data Index: 8056662 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.5320. Min Act: -0.1700
Data Index: 2907767 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4882. Min Act: -0.1700
Data Index: 7792041 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4882. Min Act: -0.1700
Data Index: 5690677 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4882. Min Act: -0.1700
Data Index: 7518788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4706. Min Act: -0.1685
Data Index: 4125221 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4618. Min Act: -0.1697
Data Index: 1732534 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4706. Min Act: -0.1700
Data Index: 3299423 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4794. Min Act: -0.1675
Data Index: 1610144 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4618. Min Act: -0.1619
Data Index: 3450272 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4706. Min Act: -0.1700
Data Index: 8433540 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4618. Min Act: -0.1667
Data Index: 1171854 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4530. Min Act: -0.1679
Data Index: 6321592 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4530. Min Act: -0.1700
Data Index: 91864 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4530. Min Act: -0.1700
Data Index: 3197712 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4530. Min Act: -0.1700
Data Index: 91868 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4442. Min Act: -0.1695
Data Index: 8134074 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4354. Min Act: -0.1617
Data Index: 3389001 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5583. Min Range: -1.5583
Max Act: 1.4442. Min Act: -0.1692
Data Index: 4990722 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19