Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4036 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.9577. Min Act: -0.1700
Data Index: 3227840 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.8015. Min Act: -0.1700
Data Index: 2339499 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.7077. Min Act: -0.1700
Data Index: 3227841 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.5827. Min Act: -0.1700
Data Index: 2339494 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.6140. Min Act: -0.1700
Data Index: 2339497 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.5827. Min Act: -0.1700
Data Index: 2339498 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.5202. Min Act: -0.1700
Data Index: 2339501 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.4890. Min Act: -0.1700
Data Index: 2339500 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.4577. Min Act: -0.1700
Data Index: 3227845 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.3327. Min Act: -0.1700
Data Index: 3227842 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.3640. Min Act: -0.1700
Data Index: 3227836 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.3640. Min Act: -0.1700
Data Index: 3227844 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.2702. Min Act: -0.1700
Data Index: 3227835 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.2390. Min Act: -0.1700
Data Index: 2339493 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.2077. Min Act: -0.1700
Data Index: 2339496 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.2077. Min Act: -0.1700
Data Index: 3227843 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.1765. Min Act: -0.1700
Data Index: 5028841 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.1765. Min Act: -0.1700
Data Index: 190431 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.1452. Min Act: -0.1700
Data Index: 3227839 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9577. Min Range: -5.9577
Max Act: 5.1765. Min Act: -0.1700
Data Index: 190422 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19