Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.9399. Min Act: -0.1700
Data Index: 5193961 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.9087. Min Act: -0.1700
Data Index: 4844 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.8462. Min Act: -0.1700
Data Index: 5312234 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.8149. Min Act: -0.1700
Data Index: 3369786 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.8149. Min Act: -0.1700
Data Index: 1498015 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.6899. Min Act: -0.1700
Data Index: 8803470 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.6587. Min Act: -0.1700
Data Index: 5947075 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.6587. Min Act: -0.1700
Data Index: 368097 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.5337. Min Act: -0.1700
Data Index: 4905496 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.5024. Min Act: -0.1700
Data Index: 7230119 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.5024. Min Act: -0.1700
Data Index: 289428 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.5337. Min Act: -0.1700
Data Index: 21578 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.4399. Min Act: -0.1700
Data Index: 8777714 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.4399. Min Act: -0.1700
Data Index: 7394645 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.4399. Min Act: -0.1700
Data Index: 739007 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.4399. Min Act: -0.1700
Data Index: 3756471 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.4087. Min Act: -0.1700
Data Index: 7942251 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.4087. Min Act: -0.1700
Data Index: 6586959 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.4087. Min Act: -0.1700
Data Index: 1395990 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9399. Min Range: -6.9399
Max Act: 6.4087. Min Act: -0.1700
Data Index: 1676528 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19