Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3523 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.6142. Min Act: -0.1700
Data Index: 8602543 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.4892. Min Act: -0.1700
Data Index: 7265647 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.4267. Min Act: -0.1700
Data Index: 4686280 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.4267. Min Act: -0.1700
Data Index: 82518 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.3955. Min Act: -0.1700
Data Index: 7241012 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.3955. Min Act: -0.1700
Data Index: 2279993 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.3017. Min Act: -0.1700
Data Index: 604793 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.3017. Min Act: -0.1700
Data Index: 171552 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2705. Min Act: -0.1700
Data Index: 145270 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2705. Min Act: -0.1700
Data Index: 5433910 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2705. Min Act: -0.1700
Data Index: 1668752 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2705. Min Act: -0.1700
Data Index: 7568073 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2705. Min Act: -0.1700
Data Index: 3839314 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2080. Min Act: -0.1700
Data Index: 2825282 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2392. Min Act: -0.1700
Data Index: 6552198 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2080. Min Act: -0.1700
Data Index: 2583608 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2080. Min Act: -0.1700
Data Index: 7655661 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2080. Min Act: -0.1700
Data Index: 2166175 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2080. Min Act: -0.1700
Data Index: 1497145 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.1767. Min Act: -0.1700
Data Index: 4869268 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19