Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.8787. Min Act: -0.1700
Data Index: 4475073 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.6599. Min Act: -0.1700
Data Index: 8541757 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.5349. Min Act: -0.1700
Data Index: 2100485 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.5037. Min Act: -0.1700
Data Index: 1260318 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.4724. Min Act: -0.1700
Data Index: 4105222 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.3474. Min Act: -0.1700
Data Index: 8125366 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.3474. Min Act: -0.1700
Data Index: 8780104 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.2849. Min Act: -0.1700
Data Index: 1443639 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.2849. Min Act: -0.1700
Data Index: 5865324 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.3162. Min Act: -0.1700
Data Index: 3600874 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.2537. Min Act: -0.1700
Data Index: 1559752 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.1912. Min Act: -0.1700
Data Index: 1328415 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.1912. Min Act: -0.1700
Data Index: 4164313 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.1912. Min Act: -0.1700
Data Index: 6627582 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.1912. Min Act: -0.1700
Data Index: 3744 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.1287. Min Act: -0.1700
Data Index: 342322 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.0974. Min Act: -0.1700
Data Index: 6282333 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.1287. Min Act: -0.1700
Data Index: 1260319 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.1287. Min Act: -0.1700
Data Index: 5552027 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8787. Min Range: -7.8787
Max Act: 7.1287. Min Act: -0.1700
Data Index: 309935 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19