Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.8927. Min Act: -0.1700
Data Index: 6884747 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.6114. Min Act: -0.1700
Data Index: 7332223 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.5489. Min Act: -0.1700
Data Index: 8475397 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.5489. Min Act: -0.1700
Data Index: 1303087 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.5177. Min Act: -0.1700
Data Index: 8038160 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.4239. Min Act: -0.1700
Data Index: 902845 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3614. Min Act: -0.1700
Data Index: 7244720 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3927. Min Act: -0.1700
Data Index: 2607664 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3927. Min Act: -0.1700
Data Index: 1403858 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3927. Min Act: -0.1700
Data Index: 134343 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3927. Min Act: -0.1700
Data Index: 4092370 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3614. Min Act: -0.1700
Data Index: 8038159 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3614. Min Act: -0.1700
Data Index: 3800189 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3302. Min Act: -0.1700
Data Index: 5861499 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.2989. Min Act: -0.1700
Data Index: 5371741 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3302. Min Act: -0.1700
Data Index: 5268570 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.2989. Min Act: -0.1700
Data Index: 4144640 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3302. Min Act: -0.1700
Data Index: 8031238 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.3302. Min Act: -0.1700
Data Index: 354450 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8927. Min Range: -5.8927
Max Act: 5.2989. Min Act: -0.1700
Data Index: 8210311 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19