Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.8040. Min Act: -0.1700
Data Index: 2143759 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.8040. Min Act: -0.1700
Data Index: 3958315 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.7415. Min Act: -0.1700
Data Index: 2820420 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.7103. Min Act: -0.1700
Data Index: 5701298 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.6790. Min Act: -0.1700
Data Index: 3972633 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.6478. Min Act: -0.1700
Data Index: 1818875 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.6478. Min Act: -0.1700
Data Index: 1446958 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.5540. Min Act: -0.1700
Data Index: 2072091 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.5540. Min Act: -0.1700
Data Index: 7954306 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.5540. Min Act: -0.1700
Data Index: 7071474 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.5540. Min Act: -0.1700
Data Index: 5637774 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.4915. Min Act: -0.1700
Data Index: 6664701 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.4915. Min Act: -0.1700
Data Index: 7419734 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.4603. Min Act: -0.1700
Data Index: 8769496 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.4290. Min Act: -0.1700
Data Index: 7767881 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.4603. Min Act: -0.1700
Data Index: 6878561 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.3978. Min Act: -0.1700
Data Index: 1033302 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.3978. Min Act: -0.1700
Data Index: 4863878 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.3978. Min Act: -0.1700
Data Index: 5922743 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8040. Min Range: -6.8040
Max Act: 6.3665. Min Act: -0.1700
Data Index: 684065 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19