Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3140 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.5890. Min Act: -0.1700
Data Index: 1854679 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.5265. Min Act: -0.1698
Data Index: 2495674 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.5265. Min Act: -0.1700
Data Index: 7647747 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.5265. Min Act: -0.1700
Data Index: 6117908 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.5265. Min Act: -0.1700
Data Index: 5227511 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.4328. Min Act: -0.1700
Data Index: 3128507 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.4328. Min Act: -0.1700
Data Index: 1079303 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.3703. Min Act: -0.1700
Data Index: 3817118 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.4015. Min Act: -0.1700
Data Index: 5682165 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.4015. Min Act: -0.1700
Data Index: 4029569 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.3703. Min Act: -0.1700
Data Index: 320687 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.3703. Min Act: -0.1700
Data Index: 362525 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.3703. Min Act: -0.1700
Data Index: 4635723 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.3390. Min Act: -0.1700
Data Index: 2379392 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.3390. Min Act: -0.1700
Data Index: 6132760 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.3390. Min Act: -0.1700
Data Index: 8426849 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.3078. Min Act: -0.1700
Data Index: 2883611 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.2765. Min Act: -0.1700
Data Index: 2694875 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.2765. Min Act: -0.1700
Data Index: 7656287 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5890. Min Range: -5.5890
Max Act: 5.2765. Min Act: -0.1700
Data Index: 1641316 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19