Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4693 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.6690. Min Act: -0.1700
Data Index: 3832445 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.6378. Min Act: -0.1700
Data Index: 5363387 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.6378. Min Act: -0.1700
Data Index: 7180853 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.5128. Min Act: -0.1700
Data Index: 8317305 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.4190. Min Act: -0.1700
Data Index: 6530539 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.4503. Min Act: -0.1700
Data Index: 5143516 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.4190. Min Act: -0.1700
Data Index: 3968814 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.3878. Min Act: -0.1700
Data Index: 1555347 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.3565. Min Act: -0.1700
Data Index: 4162955 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.3565. Min Act: -0.1700
Data Index: 5922748 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.3253. Min Act: -0.1700
Data Index: 6718617 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.2940. Min Act: -0.1700
Data Index: 7860624 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.2628. Min Act: -0.1700
Data Index: 3280266 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.2940. Min Act: -0.1700
Data Index: 8160985 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.2315. Min Act: -0.1700
Data Index: 257109 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.2628. Min Act: -0.1700
Data Index: 3053718 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.2003. Min Act: -0.1700
Data Index: 4202559 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.2003. Min Act: -0.1700
Data Index: 327240 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.1690. Min Act: -0.1700
Data Index: 3486729 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6690. Min Range: -6.6690
Max Act: 6.1690. Min Act: -0.1700
Data Index: 8590851 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19