Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2470 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.5576. Min Act: -0.1700
Data Index: 7270345 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.1513. Min Act: -0.1700
Data Index: 3102446 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.1513. Min Act: -0.1700
Data Index: 5552602 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.1201. Min Act: -0.1700
Data Index: 3300688 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.1201. Min Act: -0.1700
Data Index: 5789863 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.1201. Min Act: -0.1700
Data Index: 5717906 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.1201. Min Act: -0.1700
Data Index: 6457306 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.0576. Min Act: -0.1700
Data Index: 8462869 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.0263. Min Act: -0.1700
Data Index: 6686210 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.0263. Min Act: -0.1700
Data Index: 7797914 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5576. Min Range: -5.5576
Max Act: 5.0263. Min Act: -0.1700
Data Index: 4761027 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5576. Min Range: -5.5576
Max Act: 4.9951. Min Act: -0.1700
Data Index: 89258 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5576. Min Range: -5.5576
Max Act: 4.9951. Min Act: -0.1700
Data Index: 7540246 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5576. Min Range: -5.5576
Max Act: 4.9951. Min Act: -0.1700
Data Index: 4726937 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5576. Min Range: -5.5576
Max Act: 4.9951. Min Act: -0.1700
Data Index: 2067605 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5576. Min Range: -5.5576
Max Act: 4.9951. Min Act: -0.1700
Data Index: 1026860 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5576. Min Range: -5.5576
Max Act: 4.9638. Min Act: -0.1700
Data Index: 5027413 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5576. Min Range: -5.5576
Max Act: 4.9638. Min Act: -0.1700
Data Index: 5614254 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5576. Min Range: -5.5576
Max Act: 4.9638. Min Act: -0.1700
Data Index: 6217991 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5576. Min Range: -5.5576
Max Act: 4.9638. Min Act: -0.1700
Data Index: 2485051 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19