Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.3794. Min Act: -0.1700
Data Index: 3064614 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.2857. Min Act: -0.1700
Data Index: 4073462 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.2544. Min Act: -0.1700
Data Index: 5577648 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.2544. Min Act: -0.1700
Data Index: 2184658 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.1607. Min Act: -0.1700
Data Index: 4993471 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.1607. Min Act: -0.1700
Data Index: 4557516 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.1294. Min Act: -0.1700
Data Index: 2723837 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.1294. Min Act: -0.1700
Data Index: 6531769 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0981. Min Act: -0.1700
Data Index: 7239813 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0981. Min Act: -0.1700
Data Index: 8044673 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0669. Min Act: -0.1700
Data Index: 167450 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0669. Min Act: -0.1700
Data Index: 953284 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0981. Min Act: -0.1700
Data Index: 3119357 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0669. Min Act: -0.1700
Data Index: 7606633 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0356. Min Act: -0.1700
Data Index: 5287413 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0356. Min Act: -0.1700
Data Index: 5296796 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0356. Min Act: -0.1700
Data Index: 4021332 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0356. Min Act: -0.1700
Data Index: 2830827 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0356. Min Act: -0.1700
Data Index: 3043652 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3794. Min Range: -4.3794
Max Act: 4.0044. Min Act: -0.1700
Data Index: 1545664 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19