Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2572 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.6006. Min Act: -0.1700
Data Index: 7556134 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.5381. Min Act: -0.1700
Data Index: 136479 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.3506. Min Act: -0.1700
Data Index: 488443 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.3506. Min Act: -0.1700
Data Index: 8372722 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.2881. Min Act: -0.1700
Data Index: 6111065 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.2569. Min Act: -0.1700
Data Index: 8680251 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.1944. Min Act: -0.1700
Data Index: 605950 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.1944. Min Act: -0.1700
Data Index: 158773 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.1319. Min Act: -0.1700
Data Index: 6534906 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.1319. Min Act: -0.1700
Data Index: 7310385 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.1006. Min Act: -0.1700
Data Index: 8340583 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.1006. Min Act: -0.1700
Data Index: 6518375 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.1006. Min Act: -0.1700
Data Index: 900308 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.0381. Min Act: -0.1700
Data Index: 1930615 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6006. Min Range: -7.6006
Max Act: 7.0381. Min Act: -0.1700
Data Index: 6733926 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6006. Min Range: -7.6006
Max Act: 6.9444. Min Act: -0.1700
Data Index: 429836 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6006. Min Range: -7.6006
Max Act: 6.9756. Min Act: -0.1700
Data Index: 364505 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6006. Min Range: -7.6006
Max Act: 6.9444. Min Act: -0.1700
Data Index: 8433161 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6006. Min Range: -7.6006
Max Act: 6.9444. Min Act: -0.1700
Data Index: 5788417 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6006. Min Range: -7.6006
Max Act: 6.9444. Min Act: -0.1700
Data Index: 3359320 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19