Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.8385. Min Act: -0.1700
Data Index: 8006511 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.6510. Min Act: -0.1700
Data Index: 5903861 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.5885. Min Act: -0.1700
Data Index: 2077750 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.5260. Min Act: -0.1700
Data Index: 859198 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.4948. Min Act: -0.1700
Data Index: 3739201 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.4635. Min Act: -0.1700
Data Index: 7032750 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.4323. Min Act: -0.1700
Data Index: 3558055 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.3698. Min Act: -0.1700
Data Index: 5459607 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.3698. Min Act: -0.1700
Data Index: 4277142 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.3385. Min Act: -0.1700
Data Index: 421321 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.2760. Min Act: -0.1700
Data Index: 28570 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.2760. Min Act: -0.1700
Data Index: 8044435 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.2760. Min Act: -0.1700
Data Index: 2768207 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.2448. Min Act: -0.1700
Data Index: 6519222 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.2448. Min Act: -0.1700
Data Index: 5692740 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.2448. Min Act: -0.1700
Data Index: 1216909 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.2135. Min Act: -0.1700
Data Index: 4006933 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.2135. Min Act: -0.1700
Data Index: 1920644 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.1510. Min Act: -0.1700
Data Index: 110301 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8385. Min Range: -6.8385
Max Act: 6.2135. Min Act: -0.1700
Data Index: 2365397 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19