Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1247 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.8272. Min Act: -0.1700
Data Index: 8354019 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.7022. Min Act: -0.1700
Data Index: 3992795 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.6085. Min Act: -0.1700
Data Index: 2516617 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.5147. Min Act: -0.1700
Data Index: 4968261 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.5147. Min Act: -0.1700
Data Index: 6496470 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.4835. Min Act: -0.1700
Data Index: 4759570 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.4835. Min Act: -0.1700
Data Index: 1705501 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.4522. Min Act: -0.1700
Data Index: 6142606 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.3585. Min Act: -0.1700
Data Index: 7295318 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.3585. Min Act: -0.1700
Data Index: 8697538 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.3585. Min Act: -0.1700
Data Index: 255611 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.3272. Min Act: -0.1700
Data Index: 1057472 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.3585. Min Act: -0.1700
Data Index: 1745635 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.2960. Min Act: -0.1700
Data Index: 8484125 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.3272. Min Act: -0.1700
Data Index: 5131473 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.2647. Min Act: -0.1700
Data Index: 3624 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.2960. Min Act: -0.1700
Data Index: 5131470 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.2960. Min Act: -0.1700
Data Index: 1433935 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.2960. Min Act: -0.1700
Data Index: 7569482 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8272. Min Range: -7.8272
Max Act: 7.2647. Min Act: -0.1700
Data Index: 6411336 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19