Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.3771. Min Act: -0.1700
Data Index: 5330595 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.3146. Min Act: -0.1700
Data Index: 7556073 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.2521. Min Act: -0.1700
Data Index: 289346 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.2209. Min Act: -0.1700
Data Index: 6376978 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.2209. Min Act: -0.1700
Data Index: 2474151 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1896. Min Act: -0.1700
Data Index: 8758653 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1896. Min Act: -0.1700
Data Index: 2528507 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1896. Min Act: -0.1700
Data Index: 1758109 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1896. Min Act: -0.1700
Data Index: 4061114 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1896. Min Act: -0.1700
Data Index: 5302237 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1896. Min Act: -0.1700
Data Index: 3379012 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1896. Min Act: -0.1700
Data Index: 2080074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1584. Min Act: -0.1700
Data Index: 5582395 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1584. Min Act: -0.1700
Data Index: 5334507 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1584. Min Act: -0.1700
Data Index: 3305139 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1584. Min Act: -0.1700
Data Index: 1371272 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1584. Min Act: -0.1700
Data Index: 4371169 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1584. Min Act: -0.1700
Data Index: 3198321 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1271. Min Act: -0.1700
Data Index: 3927100 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3771. Min Range: -4.3771
Max Act: 4.1584. Min Act: -0.1700
Data Index: 735808 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19