Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4942. Min Range: -7.4942
Max Act: 7.4942. Min Act: -0.1700
Data Index: 2143236 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4942. Min Range: -7.4942
Max Act: 7.3379. Min Act: -0.1700
Data Index: 5969557 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4942. Min Range: -7.4942
Max Act: 7.1504. Min Act: -0.1700
Data Index: 4916791 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.9629. Min Act: -0.1700
Data Index: 7755026 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.8692. Min Act: -0.1700
Data Index: 7997786 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.8379. Min Act: -0.1700
Data Index: 6574922 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.8067. Min Act: -0.1700
Data Index: 7662459 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.8067. Min Act: -0.1700
Data Index: 185379 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.7754. Min Act: -0.1700
Data Index: 8431767 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.7442. Min Act: -0.1700
Data Index: 7773580 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.7754. Min Act: -0.1700
Data Index: 7728147 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.8067. Min Act: -0.1700
Data Index: 8252096 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.7442. Min Act: -0.1700
Data Index: 1382871 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.7442. Min Act: -0.1700
Data Index: 4781033 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.7129. Min Act: -0.1700
Data Index: 7380322 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.7442. Min Act: -0.1700
Data Index: 7668048 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.6504. Min Act: -0.1700
Data Index: 4197236 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.6817. Min Act: -0.1700
Data Index: 3714458 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.6504. Min Act: -0.1700
Data Index: 6499837 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4942. Min Range: -7.4942
Max Act: 6.6504. Min Act: -0.1700
Data Index: 6670248 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19