Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.9226. Min Act: -0.1700
Data Index: 1277267 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.2976. Min Act: -0.1700
Data Index: 7604283 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.2663. Min Act: -0.1700
Data Index: 4602397 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.2038. Min Act: -0.1700
Data Index: 7604282 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.2038. Min Act: -0.1700
Data Index: 236297 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.2038. Min Act: -0.1700
Data Index: 1424891 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.1413. Min Act: -0.1700
Data Index: 8379433 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.1413. Min Act: -0.1700
Data Index: 5223017 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.1101. Min Act: -0.1700
Data Index: 2486305 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.1413. Min Act: -0.1700
Data Index: 2506392 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.0788. Min Act: -0.1700
Data Index: 4200091 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.1101. Min Act: -0.1700
Data Index: 1424892 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.1101. Min Act: -0.1700
Data Index: 1152626 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.0163. Min Act: -0.1700
Data Index: 5067056 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9226. Min Range: -7.9226
Max Act: 7.0163. Min Act: -0.1700
Data Index: 7656643 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9226. Min Range: -7.9226
Max Act: 6.9538. Min Act: -0.1700
Data Index: 8574138 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9226. Min Range: -7.9226
Max Act: 6.8913. Min Act: -0.1700
Data Index: 312979 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9226. Min Range: -7.9226
Max Act: 6.9538. Min Act: -0.1700
Data Index: 8139606 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9226. Min Range: -7.9226
Max Act: 6.8913. Min Act: -0.1700
Data Index: 7093682 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9226. Min Range: -7.9226
Max Act: 6.9226. Min Act: -0.1700
Data Index: 3249152 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19