Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1065 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3503. Min Range: -5.3503
Max Act: 5.3503. Min Act: -0.1700
Data Index: 8691028 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3503. Min Range: -5.3503
Max Act: 5.2253. Min Act: -0.1700
Data Index: 597295 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3503. Min Range: -5.3503
Max Act: 5.1003. Min Act: -0.1700
Data Index: 4397936 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3503. Min Range: -5.3503
Max Act: 5.0690. Min Act: -0.1700
Data Index: 4933651 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3503. Min Range: -5.3503
Max Act: 5.1003. Min Act: -0.1700
Data Index: 715800 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3503. Min Range: -5.3503
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4988063 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3503. Min Range: -5.3503
Max Act: 5.0690. Min Act: -0.1700
Data Index: 6803980 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3503. Min Range: -5.3503
Max Act: 5.0378. Min Act: -0.1700
Data Index: 7269 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3503. Min Range: -5.3503
Max Act: 5.0065. Min Act: -0.1700
Data Index: 2481473 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3503. Min Range: -5.3503
Max Act: 5.0378. Min Act: -0.1700
Data Index: 3871696 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3503. Min Range: -5.3503
Max Act: 4.9440. Min Act: -0.1700
Data Index: 5465318 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3503. Min Range: -5.3503
Max Act: 4.9128. Min Act: -0.1700
Data Index: 4210641 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3503. Min Range: -5.3503
Max Act: 4.9128. Min Act: -0.1700
Data Index: 7163110 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3503. Min Range: -5.3503
Max Act: 4.9128. Min Act: -0.1700
Data Index: 4021534 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3503. Min Range: -5.3503
Max Act: 4.9128. Min Act: -0.1700
Data Index: 1542304 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3503. Min Range: -5.3503
Max Act: 4.9440. Min Act: -0.1700
Data Index: 3395925 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3503. Min Range: -5.3503
Max Act: 4.8815. Min Act: -0.1700
Data Index: 1225565 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3503. Min Range: -5.3503
Max Act: 4.8815. Min Act: -0.1700
Data Index: 7009021 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3503. Min Range: -5.3503
Max Act: 4.8190. Min Act: -0.1700
Data Index: 5120184 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3503. Min Range: -5.3503
Max Act: 4.8190. Min Act: -0.1700
Data Index: 5341132 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19