Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2312 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.3520. Min Act: -0.1700
Data Index: 4506228 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2582. Min Act: -0.1700
Data Index: 3786669 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 4645716 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1957. Min Act: -0.1700
Data Index: 2748570 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.2270. Min Act: -0.1700
Data Index: 4475083 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1645. Min Act: -0.1700
Data Index: 5880196 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1645. Min Act: -0.1700
Data Index: 4475078 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1332. Min Act: -0.1700
Data Index: 6736569 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1332. Min Act: -0.1700
Data Index: 6736568 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1332. Min Act: -0.1700
Data Index: 7176054 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.0707. Min Act: -0.1700
Data Index: 1429001 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.1332. Min Act: -0.1700
Data Index: 3767239 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.0707. Min Act: -0.1700
Data Index: 989711 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.0394. Min Act: -0.1700
Data Index: 4100939 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.0394. Min Act: -0.1700
Data Index: 8027870 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.0707. Min Act: -0.1700
Data Index: 1664003 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.0394. Min Act: -0.1700
Data Index: 7467059 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.0394. Min Act: -0.1700
Data Index: 5512784 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3520. Min Range: -4.3520
Max Act: 3.9769. Min Act: -0.1700
Data Index: 6777598 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3520. Min Range: -4.3520
Max Act: 4.0082. Min Act: -0.1700
Data Index: 3590840 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19