Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 951 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.5254. Min Act: -0.1700
Data Index: 7065434 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.5254. Min Act: -0.1700
Data Index: 1990427 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4930. Min Act: -0.1700
Data Index: 5961688 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4606. Min Act: -0.1700
Data Index: 1127238 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4443. Min Act: -0.1700
Data Index: 1034972 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4606. Min Act: -0.1700
Data Index: 4766812 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4280. Min Act: -0.1700
Data Index: 3770840 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4443. Min Act: -0.1700
Data Index: 2478714 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4280. Min Act: -0.1700
Data Index: 5136644 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4280. Min Act: -0.1700
Data Index: 1318758 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4117. Min Act: -0.1700
Data Index: 7770149 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4280. Min Act: -0.1700
Data Index: 5677064 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4117. Min Act: -0.1700
Data Index: 7514479 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4117. Min Act: -0.1700
Data Index: 2113972 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4117. Min Act: -0.1700
Data Index: 3327571 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4117. Min Act: -0.1700
Data Index: 7238816 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4117. Min Act: -0.1700
Data Index: 438293 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.4117. Min Act: -0.1700
Data Index: 1901619 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.3954. Min Act: -0.1700
Data Index: 129191 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5254. Min Range: -2.5254
Max Act: 2.3954. Min Act: -0.1700
Data Index: 2539617 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19