Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4072 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.5897. Min Act: -0.1700
Data Index: 6379559 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.2772. Min Act: -0.1700
Data Index: 7869878 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.2459. Min Act: -0.1700
Data Index: 6018518 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.2147. Min Act: -0.1700
Data Index: 8347856 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.2147. Min Act: -0.1700
Data Index: 5906558 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.1834. Min Act: -0.1700
Data Index: 8347847 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.1522. Min Act: -0.1700
Data Index: 6775246 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.1209. Min Act: -0.1700
Data Index: 1711210 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0897. Min Act: -0.1700
Data Index: 2942356 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.1209. Min Act: -0.1700
Data Index: 1420990 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0897. Min Act: -0.1700
Data Index: 7794557 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0584. Min Act: -0.1700
Data Index: 8315983 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0272. Min Act: -0.1700
Data Index: 2653668 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0897. Min Act: -0.1700
Data Index: 6395255 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0897. Min Act: -0.1700
Data Index: 7624771 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5897. Min Range: -5.5897
Max Act: 5.0272. Min Act: -0.1700
Data Index: 8746479 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5897. Min Range: -5.5897
Max Act: 4.9959. Min Act: -0.1700
Data Index: 3868632 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5897. Min Range: -5.5897
Max Act: 4.9959. Min Act: -0.1700
Data Index: 4631944 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5897. Min Range: -5.5897
Max Act: 4.9959. Min Act: -0.1700
Data Index: 105929 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5897. Min Range: -5.5897
Max Act: 4.9647. Min Act: -0.1700
Data Index: 8271000 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19