Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8961. Min Range: -7.8961
Max Act: 7.8961. Min Act: -0.1700
Data Index: 1073259 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8961. Min Range: -7.8961
Max Act: 7.4586. Min Act: -0.1700
Data Index: 7589512 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8961. Min Range: -7.8961
Max Act: 7.3023. Min Act: -0.1700
Data Index: 7201932 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8961. Min Range: -7.8961
Max Act: 7.1773. Min Act: -0.1700
Data Index: 8166989 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8961. Min Range: -7.8961
Max Act: 7.1461. Min Act: -0.1700
Data Index: 7337518 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.9586. Min Act: -0.1700
Data Index: 1574003 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.9273. Min Act: -0.1700
Data Index: 3193401 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.8648. Min Act: -0.1700
Data Index: 8226654 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.8648. Min Act: -0.1700
Data Index: 8370107 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.8023. Min Act: -0.1700
Data Index: 5178608 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.7711. Min Act: -0.1700
Data Index: 3626635 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.7711. Min Act: -0.1700
Data Index: 625491 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.7398. Min Act: -0.1700
Data Index: 8297633 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.7398. Min Act: -0.1700
Data Index: 2133965 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.7711. Min Act: -0.1700
Data Index: 755666 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.7086. Min Act: -0.1700
Data Index: 3966819 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.7086. Min Act: -0.1700
Data Index: 208816 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.7086. Min Act: -0.1700
Data Index: 1501726 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.6773. Min Act: -0.1700
Data Index: 8256068 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8961. Min Range: -7.8961
Max Act: 6.6461. Min Act: -0.1700
Data Index: 4645891 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19