Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 618 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.4717. Min Act: -0.1700
Data Index: 2841928 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.4405. Min Act: -0.1700
Data Index: 1552461 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.3467. Min Act: -0.1700
Data Index: 4080080 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.3467. Min Act: -0.1700
Data Index: 5974043 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.3780. Min Act: -0.1700
Data Index: 8572689 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.3155. Min Act: -0.1700
Data Index: 481812 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.3155. Min Act: -0.1700
Data Index: 4664830 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.2842. Min Act: -0.1700
Data Index: 7320861 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.2530. Min Act: -0.1700
Data Index: 4513555 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.2530. Min Act: -0.1700
Data Index: 4947597 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.2530. Min Act: -0.1700
Data Index: 6852337 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.2530. Min Act: -0.1700
Data Index: 2704768 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.2217. Min Act: -0.1700
Data Index: 8273408 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.2217. Min Act: -0.1700
Data Index: 5406839 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.2217. Min Act: -0.1700
Data Index: 6575778 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.1905. Min Act: -0.1700
Data Index: 5059225 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.1592. Min Act: -0.1700
Data Index: 973843 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.1592. Min Act: -0.1700
Data Index: 8592034 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.1592. Min Act: -0.1700
Data Index: 8148476 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4717. Min Range: -6.4717
Max Act: 6.1280. Min Act: -0.1700
Data Index: 5011344 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19