Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.8719. Min Act: -0.1700
Data Index: 3754328 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.8406. Min Act: -0.1700
Data Index: 5791548 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.7781. Min Act: -0.1700
Data Index: 7499291 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4969. Min Act: -0.1700
Data Index: 3610610 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5906. Min Act: -0.1700
Data Index: 7390067 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6219. Min Act: -0.1700
Data Index: 1351741 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5281. Min Act: -0.1700
Data Index: 1457375 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4656. Min Act: -0.1700
Data Index: 6146927 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4656. Min Act: -0.1700
Data Index: 5109878 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4344. Min Act: -0.1700
Data Index: 308330 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4344. Min Act: -0.1700
Data Index: 647610 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4656. Min Act: -0.1700
Data Index: 7256373 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4656. Min Act: -0.1700
Data Index: 203841 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4031. Min Act: -0.1700
Data Index: 4095916 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4031. Min Act: -0.1700
Data Index: 2049439 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4031. Min Act: -0.1700
Data Index: 4592342 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4031. Min Act: -0.1700
Data Index: 2966159 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.3719. Min Act: -0.1700
Data Index: 1138653 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.3406. Min Act: -0.1700
Data Index: 1525652 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.3719. Min Act: -0.1700
Data Index: 4592337 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19