Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1952 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.5368. Min Range: -9.5368
Max Act: 9.5368. Min Act: -0.1700
Data Index: 1354374 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5368. Min Range: -9.5368
Max Act: 9.3493. Min Act: -0.1700
Data Index: 5184387 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5368. Min Range: -9.5368
Max Act: 9.2868. Min Act: -0.1700
Data Index: 7119659 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5368. Min Range: -9.5368
Max Act: 9.0993. Min Act: -0.1700
Data Index: 170172 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5368. Min Range: -9.5368
Max Act: 9.0993. Min Act: -0.1700
Data Index: 6577044 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5368. Min Range: -9.5368
Max Act: 9.0993. Min Act: -0.1700
Data Index: 2684876 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5368. Min Range: -9.5368
Max Act: 9.0993. Min Act: -0.1700
Data Index: 588840 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5368. Min Range: -9.5368
Max Act: 9.0368. Min Act: -0.1700
Data Index: 3147572 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.9118. Min Act: -0.1700
Data Index: 8389876 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.9118. Min Act: -0.1700
Data Index: 6141212 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.9743. Min Act: -0.1700
Data Index: 6284871 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.9118. Min Act: -0.1700
Data Index: 5185955 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.8493. Min Act: -0.1700
Data Index: 6105831 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.9118. Min Act: -0.1700
Data Index: 5241413 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.9118. Min Act: -0.1700
Data Index: 6665837 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.9118. Min Act: -0.1700
Data Index: 4947357 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.9118. Min Act: -0.1700
Data Index: 3748725 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.9118. Min Act: -0.1700
Data Index: 6887053 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.8493. Min Act: -0.1700
Data Index: 3340775 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5368. Min Range: -9.5368
Max Act: 8.8493. Min Act: -0.1700
Data Index: 3084841 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19