Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0647. Min Range: -6.0647
Max Act: 6.0647. Min Act: -0.1700
Data Index: 7262726 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0647. Min Range: -6.0647
Max Act: 6.0022. Min Act: -0.1700
Data Index: 2239053 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.8772. Min Act: -0.1700
Data Index: 5442226 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.8459. Min Act: -0.1700
Data Index: 7321418 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.8459. Min Act: -0.1700
Data Index: 1131975 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.8459. Min Act: -0.1700
Data Index: 1951867 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.7834. Min Act: -0.1700
Data Index: 5124452 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.8147. Min Act: -0.1700
Data Index: 926454 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.7834. Min Act: -0.1700
Data Index: 5964175 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.7834. Min Act: -0.1700
Data Index: 180708 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.7522. Min Act: -0.1700
Data Index: 1313682 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.7834. Min Act: -0.1700
Data Index: 623525 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.7522. Min Act: -0.1700
Data Index: 4445867 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.7522. Min Act: -0.1700
Data Index: 6141250 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.6897. Min Act: -0.1700
Data Index: 6579215 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.6272. Min Act: -0.1700
Data Index: 2943394 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.6584. Min Act: -0.1700
Data Index: 2974768 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.6584. Min Act: -0.1700
Data Index: 7507836 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.6272. Min Act: -0.1700
Data Index: 2385692 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0647. Min Range: -6.0647
Max Act: 5.6272. Min Act: -0.1700
Data Index: 2914948 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19