Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0939. Min Range: -7.0939
Max Act: 7.0939. Min Act: -0.1700
Data Index: 2633167 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.8439. Min Act: -0.1700
Data Index: 6447176 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.8752. Min Act: -0.1700
Data Index: 4767934 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.7814. Min Act: -0.1700
Data Index: 347973 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.7189. Min Act: -0.1700
Data Index: 2297762 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.6564. Min Act: -0.1700
Data Index: 5199834 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.6564. Min Act: -0.1700
Data Index: 1848954 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.5627. Min Act: -0.1700
Data Index: 7718635 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.5314. Min Act: -0.1700
Data Index: 6984800 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.5314. Min Act: -0.1700
Data Index: 4296593 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.5314. Min Act: -0.1700
Data Index: 6273382 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.5002. Min Act: -0.1700
Data Index: 8686172 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.5002. Min Act: -0.1700
Data Index: 6434680 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.4689. Min Act: -0.1700
Data Index: 3806491 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.4689. Min Act: -0.1700
Data Index: 3512688 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.4689. Min Act: -0.1700
Data Index: 3373034 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.4689. Min Act: -0.1700
Data Index: 6109709 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.4377. Min Act: -0.1700
Data Index: 6737624 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.4377. Min Act: -0.1700
Data Index: 5628473 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0939. Min Range: -7.0939
Max Act: 6.4377. Min Act: -0.1700
Data Index: 920400 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19