Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 346 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.8725. Min Act: -0.1700
Data Index: 1481270 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.8413. Min Act: -0.1700
Data Index: 8274113 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.8100. Min Act: -0.1700
Data Index: 6791624 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.8100. Min Act: -0.1700
Data Index: 3896036 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7787. Min Act: -0.1700
Data Index: 4561899 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7787. Min Act: -0.1700
Data Index: 6823909 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7474. Min Act: -0.1700
Data Index: 4137114 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7787. Min Act: -0.1700
Data Index: 3289249 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7474. Min Act: -0.1700
Data Index: 7778781 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7474. Min Act: -0.1700
Data Index: 6713032 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7318. Min Act: -0.1700
Data Index: 5789161 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7318. Min Act: -0.1700
Data Index: 1038242 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7318. Min Act: -0.1700
Data Index: 1190334 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7318. Min Act: -0.1700
Data Index: 6478289 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7162. Min Act: -0.1700
Data Index: 6621381 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7162. Min Act: -0.1700
Data Index: 4347083 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7318. Min Act: -0.1700
Data Index: 6823908 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.6849. Min Act: -0.1700
Data Index: 7085934 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7005. Min Act: -0.1700
Data Index: 1046466 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7005. Min Act: -0.1700
Data Index: 545296 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19