Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5718 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3518. Min Range: -6.3518
Max Act: 6.3518. Min Act: -0.1700
Data Index: 6248977 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3518. Min Range: -6.3518
Max Act: 6.3206. Min Act: -0.1700
Data Index: 6947910 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3518. Min Range: -6.3518
Max Act: 6.2581. Min Act: -0.1700
Data Index: 4727796 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3518. Min Range: -6.3518
Max Act: 6.2893. Min Act: -0.1700
Data Index: 881466 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3518. Min Range: -6.3518
Max Act: 6.1956. Min Act: -0.1700
Data Index: 298973 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3518. Min Range: -6.3518
Max Act: 6.1643. Min Act: -0.1700
Data Index: 8328216 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3518. Min Range: -6.3518
Max Act: 6.1018. Min Act: -0.1700
Data Index: 7516243 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3518. Min Range: -6.3518
Max Act: 6.1018. Min Act: -0.1700
Data Index: 7870799 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3518. Min Range: -6.3518
Max Act: 6.0706. Min Act: -0.1700
Data Index: 7064804 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3518. Min Range: -6.3518
Max Act: 6.0081. Min Act: -0.1700
Data Index: 5210417 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3518. Min Range: -6.3518
Max Act: 5.9768. Min Act: -0.1700
Data Index: 7673048 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3518. Min Range: -6.3518
Max Act: 5.9768. Min Act: -0.1700
Data Index: 4243750 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3518. Min Range: -6.3518
Max Act: 5.9768. Min Act: -0.1700
Data Index: 3608690 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3518. Min Range: -6.3518
Max Act: 5.9768. Min Act: -0.1700
Data Index: 5623847 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3518. Min Range: -6.3518
Max Act: 5.9768. Min Act: -0.1700
Data Index: 103870 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3518. Min Range: -6.3518
Max Act: 5.9768. Min Act: -0.1700
Data Index: 7016751 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3518. Min Range: -6.3518
Max Act: 5.9456. Min Act: -0.1700
Data Index: 3868560 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3518. Min Range: -6.3518
Max Act: 5.9456. Min Act: -0.1700
Data Index: 751129 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3518. Min Range: -6.3518
Max Act: 5.9768. Min Act: -0.1700
Data Index: 5684199 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3518. Min Range: -6.3518
Max Act: 5.9143. Min Act: -0.1700
Data Index: 1922526 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19