Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2314 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.4773. Min Act: -0.1700
Data Index: 1973225 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.4148. Min Act: -0.1700
Data Index: 4116864 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.3523. Min Act: -0.1700
Data Index: 6664697 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.3523. Min Act: -0.1700
Data Index: 1365032 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.3211. Min Act: -0.1700
Data Index: 8493305 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.3211. Min Act: -0.1700
Data Index: 8302670 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.3211. Min Act: -0.1700
Data Index: 7328547 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.2898. Min Act: -0.1700
Data Index: 6807205 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.2898. Min Act: -0.1700
Data Index: 1275524 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.2586. Min Act: -0.1700
Data Index: 7109131 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.2586. Min Act: -0.1700
Data Index: 2651234 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.2273. Min Act: -0.1700
Data Index: 5019347 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1961. Min Act: -0.1700
Data Index: 2671707 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1961. Min Act: -0.1700
Data Index: 4082476 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1961. Min Act: -0.1700
Data Index: 291482 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.2273. Min Act: -0.1700
Data Index: 5220757 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1648. Min Act: -0.1700
Data Index: 1786311 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1648. Min Act: -0.1700
Data Index: 2719093 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1648. Min Act: -0.1700
Data Index: 2647359 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1648. Min Act: -0.1700
Data Index: 8543513 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19