Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.8280. Min Act: -0.1700
Data Index: 8525996 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.7968. Min Act: -0.1700
Data Index: 5374406 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.7343. Min Act: -0.1700
Data Index: 3821637 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.6405. Min Act: -0.1700
Data Index: 6332768 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.5780. Min Act: -0.1700
Data Index: 8005035 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.6093. Min Act: -0.1700
Data Index: 5890655 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.5780. Min Act: -0.1700
Data Index: 4504812 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.5468. Min Act: -0.1700
Data Index: 460048 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.5468. Min Act: -0.1700
Data Index: 8371452 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.5468. Min Act: -0.1700
Data Index: 5900541 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.5155. Min Act: -0.1700
Data Index: 5730331 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.5468. Min Act: -0.1700
Data Index: 3606419 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.5155. Min Act: -0.1700
Data Index: 6274688 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.4530. Min Act: -0.1700
Data Index: 3979722 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.4843. Min Act: -0.1700
Data Index: 4079034 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.4530. Min Act: -0.1700
Data Index: 7048509 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.4218. Min Act: -0.1700
Data Index: 3641014 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.4218. Min Act: -0.1700
Data Index: 5332389 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.4218. Min Act: -0.1700
Data Index: 6250949 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8280. Min Range: -5.8280
Max Act: 5.4218. Min Act: -0.1700
Data Index: 4370590 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19