Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 990 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4844. Min Act: -0.1700
Data Index: 3596959 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4844. Min Act: -0.1700
Data Index: 6439357 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4687. Min Act: -0.1700
Data Index: 1759185 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4530. Min Act: -0.1700
Data Index: 416647 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4687. Min Act: -0.1700
Data Index: 4630386 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4530. Min Act: -0.1700
Data Index: 984555 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4374. Min Act: -0.1700
Data Index: 3545890 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4374. Min Act: -0.1700
Data Index: 6637462 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4374. Min Act: -0.1700
Data Index: 5692796 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4217. Min Act: -0.1700
Data Index: 637766 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4217. Min Act: -0.1700
Data Index: 5137610 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4217. Min Act: -0.1700
Data Index: 621737 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4217. Min Act: -0.1700
Data Index: 3803168 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4060. Min Act: -0.1700
Data Index: 5047597 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4060. Min Act: -0.1700
Data Index: 3208877 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4060. Min Act: -0.1700
Data Index: 460420 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4060. Min Act: -0.1700
Data Index: 8729183 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4060. Min Act: -0.1700
Data Index: 2038055 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.4060. Min Act: -0.1700
Data Index: 5297065 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4844. Min Range: -3.4844
Max Act: 3.3903. Min Act: -0.1700
Data Index: 3086521 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19