Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4021 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.9711. Min Act: -0.1700
Data Index: 4734978 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.8773. Min Act: -0.1700
Data Index: 3428243 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.8148. Min Act: -0.1700
Data Index: 1377883 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.8148. Min Act: -0.1700
Data Index: 8714089 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.7523. Min Act: -0.1700
Data Index: 5786028 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.7523. Min Act: -0.1700
Data Index: 8479396 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.7211. Min Act: -0.1700
Data Index: 2070133 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.6586. Min Act: -0.1700
Data Index: 6408304 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.6898. Min Act: -0.1700
Data Index: 1100372 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.6586. Min Act: -0.1700
Data Index: 3559031 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.6273. Min Act: -0.1700
Data Index: 7147199 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.6586. Min Act: -0.1700
Data Index: 5149235 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.6586. Min Act: -0.1700
Data Index: 6090099 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.6586. Min Act: -0.1700
Data Index: 911009 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.5961. Min Act: -0.1700
Data Index: 2399692 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.6273. Min Act: -0.1700
Data Index: 1983021 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.6273. Min Act: -0.1700
Data Index: 4284131 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.5961. Min Act: -0.1700
Data Index: 4516887 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.5961. Min Act: -0.1700
Data Index: 6226902 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9711. Min Range: -5.9711
Max Act: 5.5648. Min Act: -0.1700
Data Index: 3384505 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19