Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5511 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.6816. Min Act: -0.1700
Data Index: 1195385 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.6191. Min Act: -0.1700
Data Index: 7854374 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.6191. Min Act: -0.1700
Data Index: 3183141 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.4941. Min Act: -0.1700
Data Index: 6996437 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.4004. Min Act: -0.1700
Data Index: 5429322 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.3691. Min Act: -0.1700
Data Index: 6517392 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.1816. Min Act: -0.1700
Data Index: 5977110 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.1816. Min Act: -0.1700
Data Index: 6769149 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.1816. Min Act: -0.1700
Data Index: 514016 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.1816. Min Act: -0.1700
Data Index: 2856071 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.1504. Min Act: -0.1700
Data Index: 4233804 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.1504. Min Act: -0.1700
Data Index: 401352 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.1191. Min Act: -0.1700
Data Index: 6180946 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.1191. Min Act: -0.1700
Data Index: 159461 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.0879. Min Act: -0.1700
Data Index: 4041929 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.0879. Min Act: -0.1700
Data Index: 3484627 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.0879. Min Act: -0.1700
Data Index: 1830785 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.0879. Min Act: -0.1699
Data Index: 580156 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.0566. Min Act: -0.1700
Data Index: 4733192 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6816. Min Range: -6.6816
Max Act: 6.0566. Min Act: -0.1700
Data Index: 4993348 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19