Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0663. Min Range: -5.0663
Max Act: 5.0663. Min Act: -0.1700
Data Index: 2752410 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.8475. Min Act: -0.1700
Data Index: 886148 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.8475. Min Act: -0.1700
Data Index: 7868740 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.8163. Min Act: -0.1700
Data Index: 5784084 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.8163. Min Act: -0.1700
Data Index: 3744798 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.7850. Min Act: -0.1700
Data Index: 1652021 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.7225. Min Act: -0.1700
Data Index: 399578 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.7225. Min Act: -0.1700
Data Index: 5467608 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.7225. Min Act: -0.1700
Data Index: 2901958 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.7225. Min Act: -0.1700
Data Index: 474299 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.7538. Min Act: -0.1700
Data Index: 7471271 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.6913. Min Act: -0.1700
Data Index: 6648530 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.6913. Min Act: -0.1700
Data Index: 6241611 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.6600. Min Act: -0.1700
Data Index: 1980787 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.7225. Min Act: -0.1700
Data Index: 1248371 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.6913. Min Act: -0.1700
Data Index: 7377194 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.6913. Min Act: -0.1700
Data Index: 4349671 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.6913. Min Act: -0.1700
Data Index: 4719900 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.6600. Min Act: -0.1700
Data Index: 1477488 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0663. Min Range: -5.0663
Max Act: 4.6600. Min Act: -0.1700
Data Index: 5617664 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19