Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6056 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2468. Min Range: -5.2468
Max Act: 5.2468. Min Act: -0.1700
Data Index: 6086089 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2468. Min Range: -5.2468
Max Act: 5.2156. Min Act: -0.1700
Data Index: 3773173 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2468. Min Range: -5.2468
Max Act: 5.1843. Min Act: -0.1700
Data Index: 8639944 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2468. Min Range: -5.2468
Max Act: 5.1843. Min Act: -0.1700
Data Index: 419171 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2468. Min Range: -5.2468
Max Act: 5.0906. Min Act: -0.1700
Data Index: 4369581 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2468. Min Range: -5.2468
Max Act: 5.0593. Min Act: -0.1700
Data Index: 7754754 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2468. Min Range: -5.2468
Max Act: 5.0906. Min Act: -0.1700
Data Index: 4330282 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9968. Min Act: -0.1700
Data Index: 797529 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2468. Min Range: -5.2468
Max Act: 5.0281. Min Act: -0.1700
Data Index: 7107025 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9968. Min Act: -0.1700
Data Index: 2344829 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9656. Min Act: -0.1700
Data Index: 966022 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9656. Min Act: -0.1700
Data Index: 1078269 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9343. Min Act: -0.1700
Data Index: 3338979 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9343. Min Act: -0.1700
Data Index: 2016745 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9343. Min Act: -0.1700
Data Index: 2019819 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9343. Min Act: -0.1700
Data Index: 8310476 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9031. Min Act: -0.1700
Data Index: 1822359 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9031. Min Act: -0.1700
Data Index: 8066963 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9031. Min Act: -0.1700
Data Index: 562288 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2468. Min Range: -5.2468
Max Act: 4.9031. Min Act: -0.1700
Data Index: 2412250 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19