Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1885 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0751. Min Range: -5.0751
Max Act: 5.0751. Min Act: -0.1700
Data Index: 7489143 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.7626. Min Act: -0.1700
Data Index: 1066403 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.7626. Min Act: -0.1700
Data Index: 4341947 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.7314. Min Act: -0.1700
Data Index: 811449 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.7314. Min Act: -0.1700
Data Index: 3856512 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.7001. Min Act: -0.1700
Data Index: 1267083 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.7001. Min Act: -0.1700
Data Index: 1446290 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.6689. Min Act: -0.1700
Data Index: 1446291 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.6376. Min Act: -0.1700
Data Index: 3364341 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.6064. Min Act: -0.1700
Data Index: 7051388 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.6064. Min Act: -0.1700
Data Index: 1934239 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.6064. Min Act: -0.1700
Data Index: 2263142 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.6064. Min Act: -0.1700
Data Index: 6451277 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.6064. Min Act: -0.1700
Data Index: 1152248 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.5751. Min Act: -0.1700
Data Index: 6487078 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.5751. Min Act: -0.1700
Data Index: 484407 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.6064. Min Act: -0.1700
Data Index: 6827571 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.5751. Min Act: -0.1700
Data Index: 1186453 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.5751. Min Act: -0.1700
Data Index: 2312052 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0751. Min Range: -5.0751
Max Act: 4.5751. Min Act: -0.1700
Data Index: 6715855 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19