Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.7122. Min Act: -0.1700
Data Index: 836095 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.6183. Min Act: -0.1700
Data Index: 6957105 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.5870. Min Act: -0.1700
Data Index: 7542871 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.5557. Min Act: -0.1700
Data Index: 8173318 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.5557. Min Act: -0.1700
Data Index: 5049106 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.5557. Min Act: -0.1700
Data Index: 5817583 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4931. Min Act: -0.1700
Data Index: 675374 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4931. Min Act: -0.1700
Data Index: 97025 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4617. Min Act: -0.1700
Data Index: 7680839 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4304. Min Act: -0.1700
Data Index: 3171311 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4304. Min Act: -0.1700
Data Index: 8201174 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3990. Min Act: -0.1700
Data Index: 6081265 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4304. Min Act: -0.1700
Data Index: 7483180 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4617. Min Act: -0.1700
Data Index: 8094763 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4304. Min Act: -0.1700
Data Index: 8646642 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4304. Min Act: -0.1700
Data Index: 7542881 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3677. Min Act: -0.1700
Data Index: 4861232 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3677. Min Act: -0.1700
Data Index: 1384437 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3677. Min Act: -0.1700
Data Index: 7425757 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3363. Min Act: -0.1700
Data Index: 6132322 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19