Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4593 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.8453. Min Act: -0.1700
Data Index: 7468009 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.8453. Min Act: -0.1700
Data Index: 4144387 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.8140. Min Act: -0.1700
Data Index: 371993 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.7203. Min Act: -0.1700
Data Index: 2019506 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.7203. Min Act: -0.1700
Data Index: 5171754 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.7203. Min Act: -0.1700
Data Index: 6770329 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.7203. Min Act: -0.1700
Data Index: 2016643 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.6890. Min Act: -0.1700
Data Index: 3773798 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.6265. Min Act: -0.1700
Data Index: 2620641 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.6265. Min Act: -0.1700
Data Index: 6736422 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.6265. Min Act: -0.1700
Data Index: 705087 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.5328. Min Act: -0.1700
Data Index: 1118796 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.5015. Min Act: -0.1700
Data Index: 8798754 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.4703. Min Act: -0.1700
Data Index: 3383854 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.5015. Min Act: -0.1700
Data Index: 7226194 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.4703. Min Act: -0.1700
Data Index: 3389600 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.4703. Min Act: -0.1700
Data Index: 2138392 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.4390. Min Act: -0.1700
Data Index: 3598918 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.4390. Min Act: -0.1700
Data Index: 5084552 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8453. Min Range: -5.8453
Max Act: 5.4078. Min Act: -0.1700
Data Index: 1713539 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19