Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3279 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2686. Min Range: -7.2686
Max Act: 7.2686. Min Act: -0.1700
Data Index: 8521868 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2686. Min Range: -7.2686
Max Act: 7.2061. Min Act: -0.1700
Data Index: 1991742 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2686. Min Range: -7.2686
Max Act: 7.1436. Min Act: -0.1700
Data Index: 4714319 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2686. Min Range: -7.2686
Max Act: 7.0499. Min Act: -0.1700
Data Index: 8562011 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2686. Min Range: -7.2686
Max Act: 7.0186. Min Act: -0.1700
Data Index: 4352216 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.9874. Min Act: -0.1700
Data Index: 187918 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2686. Min Range: -7.2686
Max Act: 7.0186. Min Act: -0.1700
Data Index: 4108980 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.9874. Min Act: -0.1700
Data Index: 2624916 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.9249. Min Act: -0.1700
Data Index: 3484292 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.9249. Min Act: -0.1700
Data Index: 3009400 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.8936. Min Act: -0.1700
Data Index: 1682841 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.8936. Min Act: -0.1700
Data Index: 3370845 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.8624. Min Act: -0.1700
Data Index: 5000231 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.7999. Min Act: -0.1700
Data Index: 7535108 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.8311. Min Act: -0.1700
Data Index: 363277 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.7686. Min Act: -0.1700
Data Index: 298751 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.7686. Min Act: -0.1700
Data Index: 8165966 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.7686. Min Act: -0.1700
Data Index: 6002994 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.7686. Min Act: -0.1700
Data Index: 5401548 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2686. Min Range: -7.2686
Max Act: 6.7374. Min Act: -0.1700
Data Index: 2512336 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19