Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4162 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.4821. Min Act: -0.1700
Data Index: 5803340 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.4821. Min Act: -0.1700
Data Index: 7459055 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.4196. Min Act: -0.1700
Data Index: 8251712 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.4196. Min Act: -0.1700
Data Index: 1402144 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.3883. Min Act: -0.1700
Data Index: 495264 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.3883. Min Act: -0.1700
Data Index: 3404228 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.4196. Min Act: -0.1700
Data Index: 5744092 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.3571. Min Act: -0.1700
Data Index: 6961804 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.3571. Min Act: -0.1700
Data Index: 6003114 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.3571. Min Act: -0.1700
Data Index: 2327440 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.3258. Min Act: -0.1700
Data Index: 731853 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.3571. Min Act: -0.1700
Data Index: 5116423 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2946. Min Act: -0.1700
Data Index: 8379579 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2946. Min Act: -0.1700
Data Index: 3811325 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2946. Min Act: -0.1700
Data Index: 1577356 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2946. Min Act: -0.1700
Data Index: 7354832 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2946. Min Act: -0.1700
Data Index: 5770585 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2946. Min Act: -0.1700
Data Index: 4158633 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2946. Min Act: -0.1700
Data Index: 4117955 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2633. Min Act: -0.1700
Data Index: 1226129 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19