Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4666 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4975. Min Range: -7.4975
Max Act: 7.4975. Min Act: -0.1700
Data Index: 7947331 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4975. Min Range: -7.4975
Max Act: 7.2475. Min Act: -0.1700
Data Index: 6947818 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4975. Min Range: -7.4975
Max Act: 7.2162. Min Act: -0.1700
Data Index: 5195023 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4975. Min Range: -7.4975
Max Act: 7.1537. Min Act: -0.1700
Data Index: 3701964 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4975. Min Range: -7.4975
Max Act: 7.0912. Min Act: -0.1700
Data Index: 7807746 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4975. Min Range: -7.4975
Max Act: 7.1225. Min Act: -0.1700
Data Index: 6443083 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4975. Min Range: -7.4975
Max Act: 7.0287. Min Act: -0.1700
Data Index: 1777874 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4975. Min Range: -7.4975
Max Act: 7.0600. Min Act: -0.1700
Data Index: 1835362 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4975. Min Range: -7.4975
Max Act: 7.0287. Min Act: -0.1700
Data Index: 5756315 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9662. Min Act: -0.1700
Data Index: 3363542 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9975. Min Act: -0.1700
Data Index: 7387327 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9662. Min Act: -0.1700
Data Index: 2248516 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9350. Min Act: -0.1700
Data Index: 2439997 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9662. Min Act: -0.1700
Data Index: 3132381 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9662. Min Act: -0.1700
Data Index: 8262575 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9350. Min Act: -0.1700
Data Index: 5180746 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9350. Min Act: -0.1700
Data Index: 4147236 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9350. Min Act: -0.1700
Data Index: 4771902 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9350. Min Act: -0.1700
Data Index: 2382922 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4975. Min Range: -7.4975
Max Act: 6.9037. Min Act: -0.1700
Data Index: 1653238 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19