Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1323 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1208. Min Range: -6.1208
Max Act: 6.0895. Min Act: -0.1700
Data Index: 66987 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1208. Min Range: -6.1208
Max Act: 6.0895. Min Act: -0.1700
Data Index: 3086201 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1208. Min Range: -6.1208
Max Act: 6.1208. Min Act: -0.1700
Data Index: 3570806 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1208. Min Range: -6.1208
Max Act: 6.0895. Min Act: -0.1700
Data Index: 4765437 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1208. Min Range: -6.1208
Max Act: 6.0270. Min Act: -0.1700
Data Index: 5978146 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.9958. Min Act: -0.1700
Data Index: 5518574 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.9958. Min Act: -0.1700
Data Index: 7561917 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.9333. Min Act: -0.1700
Data Index: 8763123 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.9333. Min Act: -0.1700
Data Index: 5821500 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.9020. Min Act: -0.1700
Data Index: 1039217 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.9020. Min Act: -0.1700
Data Index: 7305514 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.9333. Min Act: -0.1700
Data Index: 2379521 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.8708. Min Act: -0.1700
Data Index: 3180428 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.8708. Min Act: -0.1700
Data Index: 1934578 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.8708. Min Act: -0.1700
Data Index: 5098508 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.8395. Min Act: -0.1700
Data Index: 8220051 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.8395. Min Act: -0.1700
Data Index: 5861927 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.8708. Min Act: -0.1700
Data Index: 7702064 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.8083. Min Act: -0.1700
Data Index: 1392854 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1208. Min Range: -6.1208
Max Act: 5.8083. Min Act: -0.1700
Data Index: 7924982 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19