Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1114 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.6966. Min Act: -0.1700
Data Index: 3895045 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.6028. Min Act: -0.1700
Data Index: 8296580 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.5403. Min Act: -0.1700
Data Index: 2033865 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.6028. Min Act: -0.1700
Data Index: 7731744 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.5716. Min Act: -0.1700
Data Index: 6997906 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.5403. Min Act: -0.1700
Data Index: 112289 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.5091. Min Act: -0.1700
Data Index: 5024302 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.4778. Min Act: -0.1700
Data Index: 432978 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.4466. Min Act: -0.1700
Data Index: 327521 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.4466. Min Act: -0.1700
Data Index: 6305935 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.4778. Min Act: -0.1700
Data Index: 2087642 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.3841. Min Act: -0.1700
Data Index: 5099007 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.4153. Min Act: -0.1700
Data Index: 8568035 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.4153. Min Act: -0.1700
Data Index: 8774693 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.4153. Min Act: -0.1700
Data Index: 5146656 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.4153. Min Act: -0.1700
Data Index: 4965852 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.4153. Min Act: -0.1700
Data Index: 5755960 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.3841. Min Act: -0.1700
Data Index: 7202249 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.3528. Min Act: -0.1700
Data Index: 911158 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6966. Min Range: -4.6966
Max Act: 4.3841. Min Act: -0.1700
Data Index: 321740 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19