Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.7619. Min Act: -0.1700
Data Index: 1351745 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.7619. Min Act: -0.1700
Data Index: 4598628 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.6369. Min Act: -0.1700
Data Index: 2686245 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.6056. Min Act: -0.1700
Data Index: 7837283 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.5431. Min Act: -0.1700
Data Index: 4773810 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.5431. Min Act: -0.1700
Data Index: 967304 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.5119. Min Act: -0.1700
Data Index: 4516251 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.5119. Min Act: -0.1700
Data Index: 4335586 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.4806. Min Act: -0.1700
Data Index: 30051 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.4806. Min Act: -0.1700
Data Index: 6837795 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.4494. Min Act: -0.1700
Data Index: 8327006 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.4494. Min Act: -0.1700
Data Index: 7219101 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.4806. Min Act: -0.1700
Data Index: 7613590 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.4494. Min Act: -0.1700
Data Index: 2896495 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.4181. Min Act: -0.1700
Data Index: 3563200 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.4181. Min Act: -0.1700
Data Index: 2237510 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.3869. Min Act: -0.1700
Data Index: 7723242 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.3869. Min Act: -0.1700
Data Index: 7758760 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.3869. Min Act: -0.1700
Data Index: 1549287 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7619. Min Range: -6.7619
Max Act: 6.3869. Min Act: -0.1700
Data Index: 5072065 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19