Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 870 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.8317. Min Act: -0.1700
Data Index: 1506417 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.5814. Min Act: -0.1700
Data Index: 6520136 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.5814. Min Act: -0.1700
Data Index: 6614880 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.5814. Min Act: -0.1700
Data Index: 5108142 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.5032. Min Act: -0.1700
Data Index: 8349360 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.4718. Min Act: -0.1700
Data Index: 7758448 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.4562. Min Act: -0.1700
Data Index: 4445151 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.4562. Min Act: -0.1700
Data Index: 1475261 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.4405. Min Act: -0.1700
Data Index: 6288603 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.4248. Min Act: -0.1700
Data Index: 2488017 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.4248. Min Act: -0.1700
Data Index: 503727 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.3778. Min Act: -0.1700
Data Index: 8330567 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.3778. Min Act: -0.1700
Data Index: 4601093 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.3778. Min Act: -0.1700
Data Index: 4647924 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.3621. Min Act: -0.1700
Data Index: 61807 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.3778. Min Act: -0.1700
Data Index: 5989315 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.3621. Min Act: -0.1700
Data Index: 8169058 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.3621. Min Act: -0.1700
Data Index: 7450444 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.3621. Min Act: -0.1700
Data Index: 2461770 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8317. Min Range: -3.8317
Max Act: 3.3307. Min Act: -0.1700
Data Index: 6288614 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19