Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.3639. Min Act: -0.1700
Data Index: 4581037 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.2698. Min Act: -0.1700
Data Index: 4581034 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.1912. Min Act: -0.1700
Data Index: 5849212 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.1282. Min Act: -0.1700
Data Index: 7485656 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.1282. Min Act: -0.1700
Data Index: 1879587 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.1440. Min Act: -0.1700
Data Index: 2703514 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.0967. Min Act: -0.1700
Data Index: 210952 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.0810. Min Act: -0.1700
Data Index: 1880158 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.0652. Min Act: -0.1700
Data Index: 5152055 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.0810. Min Act: -0.1700
Data Index: 7984441 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.0178. Min Act: -0.1700
Data Index: 7740094 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.0336. Min Act: -0.1700
Data Index: 7643380 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.0178. Min Act: -0.1700
Data Index: 7740097 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.0020. Min Act: -0.1700
Data Index: 7953649 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3639. Min Range: -3.3639
Max Act: 3.0020. Min Act: -0.1700
Data Index: 6565511 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3639. Min Range: -3.3639
Max Act: 2.9546. Min Act: -0.1700
Data Index: 895032 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3639. Min Range: -3.3639
Max Act: 2.9546. Min Act: -0.1700
Data Index: 2151071 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3639. Min Range: -3.3639
Max Act: 2.9229. Min Act: -0.1700
Data Index: 7740100 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3639. Min Range: -3.3639
Max Act: 2.9546. Min Act: -0.1700
Data Index: 2069325 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3639. Min Range: -3.3639
Max Act: 2.9387. Min Act: -0.1700
Data Index: 7222405 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19