Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3176 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.5378. Min Act: -0.1700
Data Index: 1532175 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.5065. Min Act: -0.1700
Data Index: 6657056 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.4128. Min Act: -0.1700
Data Index: 3915146 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.4128. Min Act: -0.1700
Data Index: 1104663 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.3815. Min Act: -0.1700
Data Index: 4207305 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.3503. Min Act: -0.1700
Data Index: 1011430 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.3503. Min Act: -0.1700
Data Index: 4343022 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.2878. Min Act: -0.1700
Data Index: 2882892 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.3503. Min Act: -0.1700
Data Index: 6176554 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.3190. Min Act: -0.1700
Data Index: 741283 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.2878. Min Act: -0.1700
Data Index: 5521519 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.2878. Min Act: -0.1700
Data Index: 6401150 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.2878. Min Act: -0.1700
Data Index: 6117100 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.2878. Min Act: -0.1700
Data Index: 4545852 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.2253. Min Act: -0.1700
Data Index: 5765472 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.1940. Min Act: -0.1700
Data Index: 4134918 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.2565. Min Act: -0.1700
Data Index: 4491887 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.1940. Min Act: -0.1700
Data Index: 4506733 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.1940. Min Act: -0.1700
Data Index: 498329 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5378. Min Range: -6.5378
Max Act: 6.2253. Min Act: -0.1700
Data Index: 575469 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19