Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5723 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.4809. Min Act: -0.1700
Data Index: 8377191 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.3559. Min Act: -0.1700
Data Index: 2965195 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.2934. Min Act: -0.1700
Data Index: 541887 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.2309. Min Act: -0.1700
Data Index: 3111700 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.1684. Min Act: -0.1700
Data Index: 832091 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.1684. Min Act: -0.1700
Data Index: 125045 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.1059. Min Act: -0.1700
Data Index: 2166552 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.1059. Min Act: -0.1700
Data Index: 6283943 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.1059. Min Act: -0.1700
Data Index: 5608269 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.0434. Min Act: -0.1700
Data Index: 2306275 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.0434. Min Act: -0.1700
Data Index: 4600679 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4809. Min Range: -8.4809
Max Act: 7.9809. Min Act: -0.1700
Data Index: 7533453 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4809. Min Range: -8.4809
Max Act: 8.0434. Min Act: -0.1700
Data Index: 3928242 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4809. Min Range: -8.4809
Max Act: 7.9809. Min Act: -0.1700
Data Index: 4127985 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4809. Min Range: -8.4809
Max Act: 7.9809. Min Act: -0.1700
Data Index: 5679657 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4809. Min Range: -8.4809
Max Act: 7.9809. Min Act: -0.1700
Data Index: 5165238 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4809. Min Range: -8.4809
Max Act: 7.9809. Min Act: -0.1700
Data Index: 3941438 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4809. Min Range: -8.4809
Max Act: 7.9809. Min Act: -0.1700
Data Index: 7121072 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4809. Min Range: -8.4809
Max Act: 7.9184. Min Act: -0.1700
Data Index: 754630 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4809. Min Range: -8.4809
Max Act: 7.9184. Min Act: -0.1700
Data Index: 5756435 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19