Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2885 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.5043. Min Range: -10.5043
Max Act: 10.5043. Min Act: -0.1700
Data Index: 3590541 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5043. Min Range: -10.5043
Max Act: 10.3793. Min Act: -0.1700
Data Index: 1458666 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5043. Min Range: -10.5043
Max Act: 10.1293. Min Act: -0.1700
Data Index: 1513753 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5043. Min Range: -10.5043
Max Act: 10.0668. Min Act: -0.1700
Data Index: 1196750 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5043. Min Range: -10.5043
Max Act: 10.0668. Min Act: -0.1700
Data Index: 7201183 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5043. Min Range: -10.5043
Max Act: 10.0668. Min Act: -0.1700
Data Index: 1014261 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.9418. Min Act: -0.1700
Data Index: 3790688 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5043. Min Range: -10.5043
Max Act: 10.0043. Min Act: -0.1700
Data Index: 6399361 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.9418. Min Act: -0.1700
Data Index: 4816032 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.9418. Min Act: -0.1700
Data Index: 2857684 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.9418. Min Act: -0.1700
Data Index: 1568058 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.8793. Min Act: -0.1700
Data Index: 1044357 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.8793. Min Act: -0.1700
Data Index: 6525082 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.8168. Min Act: -0.1700
Data Index: 4817057 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.8168. Min Act: -0.1700
Data Index: 7681014 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.8793. Min Act: -0.1700
Data Index: 8274562 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.8793. Min Act: -0.1700
Data Index: 6160538 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.8793. Min Act: -0.1700
Data Index: 3522902 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.8793. Min Act: -0.1700
Data Index: 7098285 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5043. Min Range: -10.5043
Max Act: 9.8793. Min Act: -0.1700
Data Index: 381817 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19