Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6022. Min Range: -7.6022
Max Act: 7.6022. Min Act: -0.1700
Data Index: 3859068 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6022. Min Range: -7.6022
Max Act: 7.1960. Min Act: -0.1700
Data Index: 8508916 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6022. Min Range: -7.6022
Max Act: 7.1647. Min Act: -0.1700
Data Index: 5808845 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6022. Min Range: -7.6022
Max Act: 7.0085. Min Act: -0.1700
Data Index: 5839699 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.9772. Min Act: -0.1700
Data Index: 8682783 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.9460. Min Act: -0.1700
Data Index: 6296718 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.9772. Min Act: -0.1700
Data Index: 8022409 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.8522. Min Act: -0.1700
Data Index: 2271277 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.8835. Min Act: -0.1700
Data Index: 2571280 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.8210. Min Act: -0.1700
Data Index: 1285827 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.7897. Min Act: -0.1700
Data Index: 5907206 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.7897. Min Act: -0.1700
Data Index: 5887057 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.7897. Min Act: -0.1700
Data Index: 7232093 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.7585. Min Act: -0.1700
Data Index: 4283111 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.7272. Min Act: -0.1700
Data Index: 6303108 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.7585. Min Act: -0.1700
Data Index: 3874363 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.7272. Min Act: -0.1700
Data Index: 5702484 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.7272. Min Act: -0.1700
Data Index: 7415388 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.6960. Min Act: -0.1700
Data Index: 4935240 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6022. Min Range: -7.6022
Max Act: 6.6647. Min Act: -0.1700
Data Index: 7166756 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19