Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4879 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.5139. Min Act: -0.1700
Data Index: 5547994 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.4827. Min Act: -0.1700
Data Index: 7194140 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.5139. Min Act: -0.1700
Data Index: 3865720 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.3264. Min Act: -0.1700
Data Index: 7097063 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.2327. Min Act: -0.1700
Data Index: 3874749 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.1702. Min Act: -0.1700
Data Index: 1791879 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.1077. Min Act: -0.1700
Data Index: 8125797 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.0452. Min Act: -0.1700
Data Index: 8535696 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.8889. Min Act: -0.1700
Data Index: 3103290 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.8889. Min Act: -0.1700
Data Index: 7782614 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.8889. Min Act: -0.1700
Data Index: 6368052 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.8577. Min Act: -0.1700
Data Index: 5136249 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7952. Min Act: -0.1700
Data Index: 674037 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7952. Min Act: -0.1700
Data Index: 212503 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7952. Min Act: -0.1700
Data Index: 7253800 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 4952822 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7327. Min Act: -0.1700
Data Index: 5661462 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 4507323 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7327. Min Act: -0.1700
Data Index: 7727457 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 5120165 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19