Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4121. Min Range: -6.4121
Max Act: 6.4121. Min Act: -0.1700
Data Index: 4134681 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4121. Min Range: -6.4121
Max Act: 6.0059. Min Act: -0.1700
Data Index: 8764755 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4121. Min Range: -6.4121
Max Act: 6.0059. Min Act: -0.1700
Data Index: 8236256 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.9746. Min Act: -0.1700
Data Index: 1975367 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.8496. Min Act: -0.1700
Data Index: 1929246 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.8184. Min Act: -0.1700
Data Index: 3751707 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.8184. Min Act: -0.1700
Data Index: 3056777 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.8184. Min Act: -0.1700
Data Index: 6036188 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.7871. Min Act: -0.1700
Data Index: 3242596 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.8184. Min Act: -0.1700
Data Index: 4584674 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.7871. Min Act: -0.1700
Data Index: 3751705 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.7246. Min Act: -0.1700
Data Index: 2364073 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.7559. Min Act: -0.1700
Data Index: 6472618 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.7871. Min Act: -0.1700
Data Index: 3809588 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.7246. Min Act: -0.1700
Data Index: 1547747 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.6934. Min Act: -0.1700
Data Index: 3918721 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.6934. Min Act: -0.1700
Data Index: 4743370 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.7559. Min Act: -0.1700
Data Index: 4472629 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.7246. Min Act: -0.1700
Data Index: 8367543 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4121. Min Range: -6.4121
Max Act: 5.7246. Min Act: -0.1700
Data Index: 5024931 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19