Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2085. Min Range: -6.2085
Max Act: 6.2085. Min Act: -0.1700
Data Index: 5569754 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2085. Min Range: -6.2085
Max Act: 6.1772. Min Act: -0.1700
Data Index: 16324 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2085. Min Range: -6.2085
Max Act: 6.0522. Min Act: -0.1700
Data Index: 7375348 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2085. Min Range: -6.2085
Max Act: 6.0210. Min Act: -0.1700
Data Index: 4017423 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.9272. Min Act: -0.1700
Data Index: 3192541 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.8647. Min Act: -0.1700
Data Index: 1315974 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.8335. Min Act: -0.1700
Data Index: 4275486 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.7710. Min Act: -0.1700
Data Index: 7501251 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.7085. Min Act: -0.1700
Data Index: 1883558 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.6147. Min Act: -0.1700
Data Index: 2662035 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.6147. Min Act: -0.1700
Data Index: 6467559 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.6460. Min Act: -0.1700
Data Index: 3695006 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.6460. Min Act: -0.1700
Data Index: 1563849 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.5522. Min Act: -0.1700
Data Index: 3343100 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.5522. Min Act: -0.1700
Data Index: 5303264 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.5210. Min Act: -0.1700
Data Index: 5279475 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.4897. Min Act: -0.1700
Data Index: 2465233 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.5522. Min Act: -0.1700
Data Index: 1000498 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.5522. Min Act: -0.1700
Data Index: 1133176 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2085. Min Range: -6.2085
Max Act: 5.5522. Min Act: -0.1700
Data Index: 1467301 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19