Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 159 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3631. Min Range: -7.3631
Max Act: 7.3631. Min Act: -0.1700
Data Index: 6699475 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3631. Min Range: -7.3631
Max Act: 7.2069. Min Act: -0.1700
Data Index: 1009902 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3631. Min Range: -7.3631
Max Act: 7.0819. Min Act: -0.1700
Data Index: 929237 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.9881. Min Act: -0.1700
Data Index: 3394359 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8944. Min Act: -0.1700
Data Index: 3316410 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8944. Min Act: -0.1700
Data Index: 7509680 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.8006. Min Act: -0.1700
Data Index: 4208806 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.7069. Min Act: -0.1700
Data Index: 333833 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.6756. Min Act: -0.1700
Data Index: 6800931 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.6444. Min Act: -0.1700
Data Index: 4125397 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.6444. Min Act: -0.1700
Data Index: 6713773 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.6131. Min Act: -0.1700
Data Index: 7567426 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.5819. Min Act: -0.1700
Data Index: 2600641 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.6131. Min Act: -0.1700
Data Index: 7317217 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.5819. Min Act: -0.1700
Data Index: 233882 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.5506. Min Act: -0.1700
Data Index: 7799175 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.5506. Min Act: -0.1700
Data Index: 6800933 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.5506. Min Act: -0.1700
Data Index: 4770883 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.5506. Min Act: -0.1700
Data Index: 4270051 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3631. Min Range: -7.3631
Max Act: 6.5506. Min Act: -0.1700
Data Index: 3230882 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19