Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0382. Min Range: -4.0382
Max Act: 4.0382. Min Act: -0.1700
Data Index: 4951953 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.9913. Min Act: -0.1700
Data Index: 1782583 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.9601. Min Act: -0.1700
Data Index: 6429150 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.9601. Min Act: -0.1700
Data Index: 7740165 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.9288. Min Act: -0.1700
Data Index: 760804 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.9444. Min Act: -0.1700
Data Index: 7884587 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8819. Min Act: -0.1700
Data Index: 7387680 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.9132. Min Act: -0.1700
Data Index: 7124826 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8506. Min Act: -0.1700
Data Index: 1579014 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8975. Min Act: -0.1700
Data Index: 687154 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8663. Min Act: -0.1700
Data Index: 5868134 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8663. Min Act: -0.1700
Data Index: 2017269 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8506. Min Act: -0.1700
Data Index: 3805140 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8663. Min Act: -0.1700
Data Index: 4144079 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8194. Min Act: -0.1700
Data Index: 2639427 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8350. Min Act: -0.1700
Data Index: 2513477 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8506. Min Act: -0.1700
Data Index: 1716276 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8037. Min Act: -0.1700
Data Index: 7670712 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8037. Min Act: -0.1700
Data Index: 4182702 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0382. Min Range: -4.0382
Max Act: 3.8037. Min Act: -0.1700
Data Index: 5496293 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19