Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 882 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.7514. Min Act: -0.1700
Data Index: 6176802 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.3764. Min Act: -0.1700
Data Index: 5613881 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.3764. Min Act: -0.1700
Data Index: 1214752 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.3139. Min Act: -0.1700
Data Index: 4110084 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.3139. Min Act: -0.1700
Data Index: 8219465 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.3139. Min Act: -0.1700
Data Index: 2171736 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.3139. Min Act: -0.1700
Data Index: 8136567 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.3139. Min Act: -0.1700
Data Index: 7408513 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.3139. Min Act: -0.1700
Data Index: 2543974 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.2514. Min Act: -0.1700
Data Index: 6562917 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.2514. Min Act: -0.1700
Data Index: 6572502 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.2514. Min Act: -0.1700
Data Index: 668604 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.1889. Min Act: -0.1700
Data Index: 4036623 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.2514. Min Act: -0.1700
Data Index: 2152359 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.1889. Min Act: -0.1700
Data Index: 3759465 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.1889. Min Act: -0.1700
Data Index: 8506279 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.1889. Min Act: -0.1700
Data Index: 5142901 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.1889. Min Act: -0.1700
Data Index: 2103920 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.1889. Min Act: -0.1700
Data Index: 7195650 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7514. Min Range: -8.7514
Max Act: 8.1264. Min Act: -0.1700
Data Index: 5264599 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19