Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4412 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.6369. Min Act: -0.1700
Data Index: 703788 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.6994. Min Act: -0.1700
Data Index: 930763 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.6369. Min Act: -0.1700
Data Index: 3460872 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.5744. Min Act: -0.1700
Data Index: 8332122 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.5119. Min Act: -0.1700
Data Index: 6707244 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.4494. Min Act: -0.1700
Data Index: 7960710 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.3244. Min Act: -0.1700
Data Index: 2962314 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.3556. Min Act: -0.1700
Data Index: 6123567 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.2619. Min Act: -0.1700
Data Index: 6707908 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.2931. Min Act: -0.1700
Data Index: 5698660 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.2619. Min Act: -0.1700
Data Index: 1329069 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.2306. Min Act: -0.1700
Data Index: 4648444 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.2306. Min Act: -0.1700
Data Index: 2463935 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.1994. Min Act: -0.1700
Data Index: 2030533 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.1994. Min Act: -0.1700
Data Index: 4614589 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.1994. Min Act: -0.1700
Data Index: 2778476 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.1681. Min Act: -0.1700
Data Index: 6647580 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.1369. Min Act: -0.1700
Data Index: 2192055 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.1369. Min Act: -0.1700
Data Index: 5492668 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6994. Min Range: -7.6994
Max Act: 7.1056. Min Act: -0.1700
Data Index: 4914099 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19