Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4065 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.6940. Min Act: -0.1700
Data Index: 4880901 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.6628. Min Act: -0.1700
Data Index: 5253194 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.6315. Min Act: -0.1700
Data Index: 7547678 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.6003. Min Act: -0.1700
Data Index: 7013030 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.5690. Min Act: -0.1700
Data Index: 7490570 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.5690. Min Act: -0.1700
Data Index: 3731839 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.5065. Min Act: -0.1700
Data Index: 1186341 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.4440. Min Act: -0.1700
Data Index: 2423503 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.4440. Min Act: -0.1700
Data Index: 2955293 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.4440. Min Act: -0.1700
Data Index: 1115380 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.4440. Min Act: -0.1700
Data Index: 6200571 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.3503. Min Act: -0.1700
Data Index: 4731912 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.3503. Min Act: -0.1700
Data Index: 1419968 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.4128. Min Act: -0.1700
Data Index: 272811 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.3190. Min Act: -0.1700
Data Index: 67378 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.2878. Min Act: -0.1700
Data Index: 4809617 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.2565. Min Act: -0.1700
Data Index: 1806300 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.2878. Min Act: -0.1700
Data Index: 6628044 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.2565. Min Act: -0.1700
Data Index: 1649530 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6940. Min Range: -7.6940
Max Act: 7.2878. Min Act: -0.1700
Data Index: 3810954 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19