Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1857. Min Range: -5.1857
Max Act: 5.1857. Min Act: -0.1700
Data Index: 1336972 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1857. Min Range: -5.1857
Max Act: 5.0920. Min Act: -0.1700
Data Index: 5515625 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1857. Min Range: -5.1857
Max Act: 5.0295. Min Act: -0.1700
Data Index: 1340817 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1857. Min Range: -5.1857
Max Act: 5.0295. Min Act: -0.1700
Data Index: 4953244 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1857. Min Range: -5.1857
Max Act: 5.0295. Min Act: -0.1700
Data Index: 605793 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9982. Min Act: -0.1700
Data Index: 3663908 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1857. Min Range: -5.1857
Max Act: 5.0295. Min Act: -0.1700
Data Index: 1071140 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9982. Min Act: -0.1700
Data Index: 4227554 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9982. Min Act: -0.1700
Data Index: 1180380 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9982. Min Act: -0.1700
Data Index: 4875380 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9982. Min Act: -0.1700
Data Index: 5316487 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9982. Min Act: -0.1700
Data Index: 732632 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9357. Min Act: -0.1700
Data Index: 8439360 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9670. Min Act: -0.1700
Data Index: 952033 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9357. Min Act: -0.1700
Data Index: 5739868 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9670. Min Act: -0.1700
Data Index: 2298424 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9357. Min Act: -0.1700
Data Index: 7859148 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9357. Min Act: -0.1700
Data Index: 6522942 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9357. Min Act: -0.1700
Data Index: 5462959 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1857. Min Range: -5.1857
Max Act: 4.9357. Min Act: -0.1700
Data Index: 8202523 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19