Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1997 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.6184. Min Act: -0.1700
Data Index: 2180976 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.2747. Min Act: -0.1700
Data Index: 558429 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.2747. Min Act: -0.1700
Data Index: 5943595 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.2747. Min Act: -0.1700
Data Index: 2394094 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.2434. Min Act: -0.1700
Data Index: 6008524 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.2434. Min Act: -0.1700
Data Index: 119449 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.2434. Min Act: -0.1700
Data Index: 4991095 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1809. Min Act: -0.1700
Data Index: 7908781 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1809. Min Act: -0.1700
Data Index: 1453519 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1809. Min Act: -0.1700
Data Index: 3191484 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1497. Min Act: -0.1700
Data Index: 5125330 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1497. Min Act: -0.1700
Data Index: 591257 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1497. Min Act: -0.1700
Data Index: 8377949 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1497. Min Act: -0.1700
Data Index: 383287 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1184. Min Act: -0.1700
Data Index: 6757005 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1497. Min Act: -0.1700
Data Index: 1144844 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1184. Min Act: -0.1700
Data Index: 7383869 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1184. Min Act: -0.1700
Data Index: 7748374 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1497. Min Act: -0.1700
Data Index: 922816 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6184. Min Range: -6.6184
Max Act: 6.1497. Min Act: -0.1700
Data Index: 6532492 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19