Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4248. Min Range: -6.4248
Max Act: 6.4248. Min Act: -0.1700
Data Index: 7824936 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4248. Min Range: -6.4248
Max Act: 6.3623. Min Act: -0.1700
Data Index: 2944819 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4248. Min Range: -6.4248
Max Act: 6.2373. Min Act: -0.1700
Data Index: 7327053 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4248. Min Range: -6.4248
Max Act: 6.1123. Min Act: -0.1700
Data Index: 6097167 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4248. Min Range: -6.4248
Max Act: 6.0186. Min Act: -0.1700
Data Index: 1719432 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.9248. Min Act: -0.1700
Data Index: 1270530 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.9248. Min Act: -0.1700
Data Index: 3619386 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.9248. Min Act: -0.1700
Data Index: 4527626 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.8936. Min Act: -0.1700
Data Index: 5747080 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.8936. Min Act: -0.1700
Data Index: 8396681 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.8623. Min Act: -0.1700
Data Index: 3119623 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.8311. Min Act: -0.1700
Data Index: 5429679 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.7998. Min Act: -0.1700
Data Index: 5518795 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.8311. Min Act: -0.1700
Data Index: 4539490 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.7686. Min Act: -0.1700
Data Index: 1840324 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.7686. Min Act: -0.1700
Data Index: 7282924 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.7998. Min Act: -0.1700
Data Index: 1239078 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.7373. Min Act: -0.1700
Data Index: 1511578 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.7373. Min Act: -0.1700
Data Index: 4479639 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4248. Min Range: -6.4248
Max Act: 5.7373. Min Act: -0.1700
Data Index: 5712091 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19