Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 694 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4068. Min Range: -6.4068
Max Act: 6.4068. Min Act: -0.1700
Data Index: 1032281 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4068. Min Range: -6.4068
Max Act: 6.2506. Min Act: -0.1700
Data Index: 4833406 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4068. Min Range: -6.4068
Max Act: 6.1568. Min Act: -0.1700
Data Index: 3497879 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4068. Min Range: -6.4068
Max Act: 6.0943. Min Act: -0.1700
Data Index: 5597570 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4068. Min Range: -6.4068
Max Act: 6.0631. Min Act: -0.1700
Data Index: 3842944 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.9693. Min Act: -0.1700
Data Index: 664390 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.9381. Min Act: -0.1700
Data Index: 6552698 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.9068. Min Act: -0.1700
Data Index: 395573 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.8756. Min Act: -0.1700
Data Index: 2691570 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.8443. Min Act: -0.1700
Data Index: 1349979 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.8443. Min Act: -0.1700
Data Index: 1598177 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4667431 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.8756. Min Act: -0.1700
Data Index: 1722373 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.8131. Min Act: -0.1700
Data Index: 4010958 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.8131. Min Act: -0.1700
Data Index: 1955850 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.7818. Min Act: -0.1700
Data Index: 3953451 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.7818. Min Act: -0.1700
Data Index: 3075246 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.7506. Min Act: -0.1700
Data Index: 4066549 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.7506. Min Act: -0.1700
Data Index: 3867782 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4068. Min Range: -6.4068
Max Act: 5.7506. Min Act: -0.1700
Data Index: 708083 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19