Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1729 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.8283. Min Act: -0.1700
Data Index: 3195710 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.5158. Min Act: -0.1700
Data Index: 1176654 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.3908. Min Act: -0.1700
Data Index: 5176021 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.3596. Min Act: -0.1700
Data Index: 1765991 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.2033. Min Act: -0.1700
Data Index: 5094412 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.1721. Min Act: -0.1700
Data Index: 7872601 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.1721. Min Act: -0.1700
Data Index: 6124275 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.1096. Min Act: -0.1700
Data Index: 1253946 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.0783. Min Act: -0.1700
Data Index: 1654917 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.0783. Min Act: -0.1700
Data Index: 4001108 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.0783. Min Act: -0.1700
Data Index: 1216424 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.0471. Min Act: -0.1700
Data Index: 8696948 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8283. Min Range: -6.8283
Max Act: 6.0471. Min Act: -0.1700
Data Index: 372512 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8283. Min Range: -6.8283
Max Act: 5.9846. Min Act: -0.1700
Data Index: 8143741 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8283. Min Range: -6.8283
Max Act: 5.9533. Min Act: -0.1700
Data Index: 5822515 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8283. Min Range: -6.8283
Max Act: 5.9846. Min Act: -0.1700
Data Index: 4067357 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8283. Min Range: -6.8283
Max Act: 5.9533. Min Act: -0.1700
Data Index: 1885175 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8283. Min Range: -6.8283
Max Act: 5.9533. Min Act: -0.1700
Data Index: 6442998 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8283. Min Range: -6.8283
Max Act: 5.9533. Min Act: -0.1700
Data Index: 5888537 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8283. Min Range: -6.8283
Max Act: 5.9221. Min Act: -0.1700
Data Index: 3127167 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19