Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.4426. Min Act: -0.1700
Data Index: 386755 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.4426. Min Act: -0.1700
Data Index: 7806613 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.4113. Min Act: -0.1700
Data Index: 3082667 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.4113. Min Act: -0.1700
Data Index: 2577285 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.4113. Min Act: -0.1700
Data Index: 8273221 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.4113. Min Act: -0.1700
Data Index: 1646983 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 5432680 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 755521 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 190656 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 4726564 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.4113. Min Act: -0.1700
Data Index: 741197 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 2439218 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 2460419 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 8438774 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 8454619 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 1358452 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 2080969 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 235563 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 866785 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4426. Min Range: -3.4426
Max Act: 3.3799. Min Act: -0.1700
Data Index: 2910611 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19