Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2951 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.7401. Min Act: -0.1700
Data Index: 6816997 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.7089. Min Act: -0.1700
Data Index: 385534 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.3964. Min Act: -0.1700
Data Index: 2739528 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.3651. Min Act: -0.1700
Data Index: 8534565 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.3339. Min Act: -0.1700
Data Index: 6140174 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.2401. Min Act: -0.1700
Data Index: 5876384 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.2401. Min Act: -0.1700
Data Index: 4052347 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.2401. Min Act: -0.1700
Data Index: 8537192 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.2089. Min Act: -0.1700
Data Index: 4778845 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.1776. Min Act: -0.1700
Data Index: 4892136 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.1776. Min Act: -0.1700
Data Index: 3153300 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.1776. Min Act: -0.1700
Data Index: 4630916 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.1464. Min Act: -0.1700
Data Index: 3991365 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.1776. Min Act: -0.1700
Data Index: 1053422 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.1464. Min Act: -0.1700
Data Index: 7747500 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.1151. Min Act: -0.1700
Data Index: 7234529 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.1464. Min Act: -0.1700
Data Index: 6164467 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.1151. Min Act: -0.1700
Data Index: 3838086 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.0526. Min Act: -0.1700
Data Index: 6464700 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7401. Min Range: -6.7401
Max Act: 6.0839. Min Act: -0.1700
Data Index: 257703 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19