Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.5381. Min Act: -0.1700
Data Index: 6591371 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3819. Min Act: -0.1697
Data Index: 1919737 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3819. Min Act: -0.1699
Data Index: 3676140 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 3588548 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1699
Data Index: 3088118 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 4021440 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3194. Min Act: -0.1694
Data Index: 8624328 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 616064 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1698
Data Index: 4053056 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 3331776 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 5273113 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 2856609 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 6147248 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 1233465 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1698
Data Index: 605937 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1690
Data Index: 6138887 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 5920737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1688
Data Index: 801208 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.3506. Min Act: -0.1699
Data Index: 5820054 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5381. Min Range: -6.5381
Max Act: 6.2881. Min Act: -0.1700
Data Index: 168980 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19