Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 702 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.9388. Min Act: -0.1700
Data Index: 7316957 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.6888. Min Act: -0.1700
Data Index: 6674054 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.6888. Min Act: -0.1700
Data Index: 4349273 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.6575. Min Act: -0.1700
Data Index: 6321900 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.6263. Min Act: -0.1700
Data Index: 133283 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.6263. Min Act: -0.1700
Data Index: 120419 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.6263. Min Act: -0.1700
Data Index: 120420 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.5638. Min Act: -0.1700
Data Index: 2096913 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.5638. Min Act: -0.1700
Data Index: 996947 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.5013. Min Act: -0.1700
Data Index: 8556254 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.5013. Min Act: -0.1700
Data Index: 3507465 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.5325. Min Act: -0.1700
Data Index: 5864094 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.4700. Min Act: -0.1700
Data Index: 7209712 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.4388. Min Act: -0.1700
Data Index: 4400880 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.4388. Min Act: -0.1700
Data Index: 2763019 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.4075. Min Act: -0.1700
Data Index: 7442518 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.4075. Min Act: -0.1700
Data Index: 308215 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.4075. Min Act: -0.1700
Data Index: 8683468 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.4075. Min Act: -0.1700
Data Index: 2845534 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9388. Min Range: -5.9388
Max Act: 5.3763. Min Act: -0.1700
Data Index: 4715828 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19