Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1566 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.4043. Min Act: -0.1698
Data Index: 6573416 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3880. Min Act: -0.1697
Data Index: 3422480 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3716. Min Act: -0.1700
Data Index: 2999405 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1700
Data Index: 3886863 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1700
Data Index: 1992203 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1679
Data Index: 8041250 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1700
Data Index: 7866142 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1700
Data Index: 6733028 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1700
Data Index: 5231617 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1689
Data Index: 4993267 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1633
Data Index: 4981239 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1657
Data Index: 4669678 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3389. Min Act: -0.1700
Data Index: 289198 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1650
Data Index: 4446812 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1700
Data Index: 4401290 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1700
Data Index: 1671210 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3553. Min Act: -0.1696
Data Index: 950908 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3389. Min Act: -0.1699
Data Index: 3935437 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3225. Min Act: -0.1700
Data Index: 800138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4043. Min Range: -2.4043
Max Act: 2.3225. Min Act: -0.1700
Data Index: 3273271 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19