Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0202. Min Range: -8.0202
Max Act: 8.0202. Min Act: -0.1700
Data Index: 3925625 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0202. Min Range: -8.0202
Max Act: 7.4889. Min Act: -0.1700
Data Index: 6731726 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0202. Min Range: -8.0202
Max Act: 7.3327. Min Act: -0.1700
Data Index: 8464724 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0202. Min Range: -8.0202
Max Act: 7.3327. Min Act: -0.1700
Data Index: 8352627 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0202. Min Range: -8.0202
Max Act: 7.3014. Min Act: -0.1700
Data Index: 1357261 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0202. Min Range: -8.0202
Max Act: 7.2389. Min Act: -0.1700
Data Index: 5849553 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0202. Min Range: -8.0202
Max Act: 7.1764. Min Act: -0.1700
Data Index: 2679793 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0202. Min Range: -8.0202
Max Act: 7.1139. Min Act: -0.1700
Data Index: 6474367 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0202. Min Range: -8.0202
Max Act: 7.0514. Min Act: -0.1700
Data Index: 7371143 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0202. Min Range: -8.0202
Max Act: 7.0202. Min Act: -0.1700
Data Index: 975322 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0202. Min Range: -8.0202
Max Act: 6.9889. Min Act: -0.1700
Data Index: 2315093 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0202. Min Range: -8.0202
Max Act: 6.9889. Min Act: -0.1700
Data Index: 3137284 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0202. Min Range: -8.0202
Max Act: 6.9577. Min Act: -0.1700
Data Index: 1360716 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0202. Min Range: -8.0202
Max Act: 6.9577. Min Act: -0.1700
Data Index: 7071392 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0202. Min Range: -8.0202
Max Act: 6.9577. Min Act: -0.1700
Data Index: 3116452 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0202. Min Range: -8.0202
Max Act: 6.8639. Min Act: -0.1700
Data Index: 7124739 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0202. Min Range: -8.0202
Max Act: 6.8639. Min Act: -0.1700
Data Index: 2979470 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0202. Min Range: -8.0202
Max Act: 6.8014. Min Act: -0.1700
Data Index: 3257468 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0202. Min Range: -8.0202
Max Act: 6.8014. Min Act: -0.1700
Data Index: 7075993 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0202. Min Range: -8.0202
Max Act: 6.8327. Min Act: -0.1700
Data Index: 8085807 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19