Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2385. Min Range: -6.2385
Max Act: 6.2385. Min Act: -0.1700
Data Index: 5928289 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2385. Min Range: -6.2385
Max Act: 6.2072. Min Act: -0.1700
Data Index: 1576074 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2385. Min Range: -6.2385
Max Act: 6.1447. Min Act: -0.1700
Data Index: 413336 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2385. Min Range: -6.2385
Max Act: 6.1135. Min Act: -0.1700
Data Index: 6183232 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.9572. Min Act: -0.1700
Data Index: 7624911 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.9885. Min Act: -0.1700
Data Index: 3494294 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.9260. Min Act: -0.1700
Data Index: 188753 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.8635. Min Act: -0.1700
Data Index: 4191114 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.8635. Min Act: -0.1700
Data Index: 2136488 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.8635. Min Act: -0.1700
Data Index: 7751125 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.8322. Min Act: -0.1700
Data Index: 5583153 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.8010. Min Act: -0.1700
Data Index: 2607131 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.7697. Min Act: -0.1700
Data Index: 5325061 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.7385. Min Act: -0.1700
Data Index: 5738591 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.7385. Min Act: -0.1700
Data Index: 5456803 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.7385. Min Act: -0.1700
Data Index: 5616908 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.7385. Min Act: -0.1700
Data Index: 5315807 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.7072. Min Act: -0.1700
Data Index: 1517904 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.7697. Min Act: -0.1700
Data Index: 6523485 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2385. Min Range: -6.2385
Max Act: 5.7385. Min Act: -0.1700
Data Index: 3996943 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19