Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0381. Min Range: -6.0381
Max Act: 6.0381. Min Act: -0.1700
Data Index: 6085276 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.6943. Min Act: -0.1700
Data Index: 5098437 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.6006. Min Act: -0.1700
Data Index: 951229 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.4131. Min Act: -0.1700
Data Index: 2341296 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.3818. Min Act: -0.1700
Data Index: 4543932 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.3193. Min Act: -0.1700
Data Index: 407243 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.2568. Min Act: -0.1700
Data Index: 3553268 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.2568. Min Act: -0.1700
Data Index: 7535796 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.2568. Min Act: -0.1700
Data Index: 7038335 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.2881. Min Act: -0.1700
Data Index: 8196297 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.2568. Min Act: -0.1700
Data Index: 8698041 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.2256. Min Act: -0.1700
Data Index: 78178 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.2256. Min Act: -0.1700
Data Index: 3682904 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.1943. Min Act: -0.1700
Data Index: 3541510 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.1943. Min Act: -0.1700
Data Index: 7103068 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.1943. Min Act: -0.1700
Data Index: 2759210 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.1943. Min Act: -0.1700
Data Index: 3738754 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.1631. Min Act: -0.1700
Data Index: 5274402 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.1943. Min Act: -0.1700
Data Index: 1355416 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0381. Min Range: -6.0381
Max Act: 5.1943. Min Act: -0.1700
Data Index: 7640082 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19