Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3539 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.4987. Min Act: -0.1700
Data Index: 6172333 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.4362. Min Act: -0.1700
Data Index: 2768743 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.3112. Min Act: -0.1700
Data Index: 2764379 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.2487. Min Act: -0.1700
Data Index: 6150475 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.2487. Min Act: -0.1700
Data Index: 2738596 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.2487. Min Act: -0.1700
Data Index: 6150465 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.1862. Min Act: -0.1700
Data Index: 6267768 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.1862. Min Act: -0.1700
Data Index: 4718161 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.1862. Min Act: -0.1700
Data Index: 1590904 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.0924. Min Act: -0.1700
Data Index: 6330173 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.1237. Min Act: -0.1700
Data Index: 3315453 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.1237. Min Act: -0.1700
Data Index: 6108847 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.0299. Min Act: -0.1700
Data Index: 724053 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.0612. Min Act: -0.1700
Data Index: 5073056 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4987. Min Range: -8.4987
Max Act: 7.9674. Min Act: -0.1700
Data Index: 129967 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4987. Min Range: -8.4987
Max Act: 7.9987. Min Act: -0.1700
Data Index: 6273715 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4987. Min Range: -8.4987
Max Act: 8.0299. Min Act: -0.1700
Data Index: 281551 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4987. Min Range: -8.4987
Max Act: 7.9362. Min Act: -0.1700
Data Index: 749709 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4987. Min Range: -8.4987
Max Act: 7.9674. Min Act: -0.1700
Data Index: 4145024 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4987. Min Range: -8.4987
Max Act: 7.9674. Min Act: -0.1700
Data Index: 4910234 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19