Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.5734. Min Act: -0.1700
Data Index: 5692534 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.4796. Min Act: -0.1700
Data Index: 3160307 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.3859. Min Act: -0.1700
Data Index: 3589120 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.3234. Min Act: -0.1700
Data Index: 5780054 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1984. Min Act: -0.1700
Data Index: 1251041 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1984. Min Act: -0.1700
Data Index: 4558095 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1984. Min Act: -0.1700
Data Index: 3725980 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1671. Min Act: -0.1700
Data Index: 4476435 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1671. Min Act: -0.1700
Data Index: 563519 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1359. Min Act: -0.1700
Data Index: 3598201 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1359. Min Act: -0.1700
Data Index: 7968599 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1359. Min Act: -0.1700
Data Index: 2418301 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1046. Min Act: -0.1700
Data Index: 3598186 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1046. Min Act: -0.1700
Data Index: 7968608 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1046. Min Act: -0.1700
Data Index: 4587819 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.0734. Min Act: -0.1700
Data Index: 3184276 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.0734. Min Act: -0.1700
Data Index: 6464315 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1046. Min Act: -0.1700
Data Index: 2234755 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.0734. Min Act: -0.1700
Data Index: 7245803 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5734. Min Range: -6.5734
Max Act: 6.1046. Min Act: -0.1700
Data Index: 6782388 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19