Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2701 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1675. Min Act: -0.1700
Data Index: 5445538 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1988. Min Act: -0.1700
Data Index: 5588072 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1363. Min Act: -0.1700
Data Index: 7747011 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1363. Min Act: -0.1700
Data Index: 7131933 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1363. Min Act: -0.1700
Data Index: 8206374 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1363. Min Act: -0.1700
Data Index: 7088553 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1363. Min Act: -0.1700
Data Index: 2839349 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1363. Min Act: -0.1700
Data Index: 5983277 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1050. Min Act: -0.1700
Data Index: 7119563 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1050. Min Act: -0.1700
Data Index: 396118 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1050. Min Act: -0.1700
Data Index: 3389136 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0738. Min Act: -0.1700
Data Index: 2307323 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0738. Min Act: -0.1700
Data Index: 5859130 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0738. Min Act: -0.1700
Data Index: 8506356 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0738. Min Act: -0.1700
Data Index: 6149350 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0738. Min Act: -0.1700
Data Index: 1974074 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0425. Min Act: -0.1700
Data Index: 2047228 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0425. Min Act: -0.1700
Data Index: 827739 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0425. Min Act: -0.1700
Data Index: 3936900 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0425. Min Act: -0.1700
Data Index: 6851524 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19