Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4571 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1041. Min Range: -5.1041
Max Act: 5.1041. Min Act: -0.1700
Data Index: 2739895 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1041. Min Range: -5.1041
Max Act: 5.0103. Min Act: -0.1700
Data Index: 2396925 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.9478. Min Act: -0.1700
Data Index: 8751201 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.9478. Min Act: -0.1700
Data Index: 6643098 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.9166. Min Act: -0.1700
Data Index: 6773976 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.8228. Min Act: -0.1700
Data Index: 5822351 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.7603. Min Act: -0.1700
Data Index: 5961036 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.7916. Min Act: -0.1699
Data Index: 2775673 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.7603. Min Act: -0.1700
Data Index: 8589672 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.6978. Min Act: -0.1700
Data Index: 2316571 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.6978. Min Act: -0.1700
Data Index: 4959928 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.7291. Min Act: -0.1700
Data Index: 341965 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.7291. Min Act: -0.1700
Data Index: 2671232 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.7291. Min Act: -0.1700
Data Index: 2090455 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.6978. Min Act: -0.1700
Data Index: 6531208 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.7291. Min Act: -0.1700
Data Index: 1406789 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.6978. Min Act: -0.1700
Data Index: 706115 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.6978. Min Act: -0.1700
Data Index: 7509528 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.6978. Min Act: -0.1700
Data Index: 8022835 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1041. Min Range: -5.1041
Max Act: 4.7291. Min Act: -0.1700
Data Index: 5314802 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19