Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1579 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.9560. Min Act: -0.1700
Data Index: 6901446 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.7060. Min Act: -0.1700
Data Index: 3375531 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.6748. Min Act: -0.1700
Data Index: 584861 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.6435. Min Act: -0.1700
Data Index: 6817936 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.6435. Min Act: -0.1700
Data Index: 2168744 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.5810. Min Act: -0.1700
Data Index: 1310338 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.5810. Min Act: -0.1700
Data Index: 1380204 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.5498. Min Act: -0.1700
Data Index: 6886126 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.5498. Min Act: -0.1700
Data Index: 809548 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.5185. Min Act: -0.1700
Data Index: 8540503 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.5185. Min Act: -0.1700
Data Index: 2359171 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.4873. Min Act: -0.1700
Data Index: 5564329 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.4873. Min Act: -0.1700
Data Index: 5626504 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.4873. Min Act: -0.1700
Data Index: 4602097 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.4873. Min Act: -0.1700
Data Index: 2877982 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.4873. Min Act: -0.1700
Data Index: 7417586 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.4873. Min Act: -0.1700
Data Index: 4298070 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.4873. Min Act: -0.1700
Data Index: 7734310 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.4248. Min Act: -0.1700
Data Index: 6672504 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9560. Min Range: -6.9560
Max Act: 6.4560. Min Act: -0.1700
Data Index: 5086543 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19