Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2267 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1808. Min Range: -5.1808
Max Act: 5.1808. Min Act: -0.1700
Data Index: 2228113 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.9621. Min Act: -0.1700
Data Index: 4377402 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.9621. Min Act: -0.1700
Data Index: 5365690 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.9308. Min Act: -0.1700
Data Index: 340407 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.8996. Min Act: -0.1700
Data Index: 2001880 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.8996. Min Act: -0.1700
Data Index: 4741602 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.8996. Min Act: -0.1700
Data Index: 1948495 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.8371. Min Act: -0.1700
Data Index: 2293243 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.7746. Min Act: -0.1700
Data Index: 5365691 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.8058. Min Act: -0.1700
Data Index: 528343 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.7746. Min Act: -0.1700
Data Index: 2590463 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.7433. Min Act: -0.1700
Data Index: 2204504 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.7433. Min Act: -0.1700
Data Index: 7751373 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.7433. Min Act: -0.1700
Data Index: 1705286 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.7433. Min Act: -0.1700
Data Index: 5365689 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.7121. Min Act: -0.1700
Data Index: 1628311 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.7121. Min Act: -0.1700
Data Index: 2816648 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.7121. Min Act: -0.1700
Data Index: 8219724 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.6496. Min Act: -0.1700
Data Index: 6849765 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1808. Min Range: -5.1808
Max Act: 4.6183. Min Act: -0.1700
Data Index: 7778375 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19