Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.2374. Min Act: -0.1700
Data Index: 5731077 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.1749. Min Act: -0.1700
Data Index: 3492489 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.1749. Min Act: -0.1700
Data Index: 1233086 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.1436. Min Act: -0.1700
Data Index: 3626339 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.1124. Min Act: -0.1700
Data Index: 5090932 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.1124. Min Act: -0.1700
Data Index: 4530227 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.1124. Min Act: -0.1700
Data Index: 7723457 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.0811. Min Act: -0.1700
Data Index: 7185745 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.0811. Min Act: -0.1700
Data Index: 4787371 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.0499. Min Act: -0.1700
Data Index: 1061109 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2374. Min Range: -5.2374
Max Act: 5.0499. Min Act: -0.1700
Data Index: 3345960 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2374. Min Range: -5.2374
Max Act: 4.9874. Min Act: -0.1700
Data Index: 2937118 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2374. Min Range: -5.2374
Max Act: 4.9874. Min Act: -0.1700
Data Index: 4092164 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2374. Min Range: -5.2374
Max Act: 4.9561. Min Act: -0.1700
Data Index: 2402339 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2374. Min Range: -5.2374
Max Act: 4.7999. Min Act: -0.1700
Data Index: 961506 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2374. Min Range: -5.2374
Max Act: 4.7999. Min Act: -0.1700
Data Index: 5556670 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2374. Min Range: -5.2374
Max Act: 4.7374. Min Act: -0.1700
Data Index: 961507 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2374. Min Range: -5.2374
Max Act: 4.7374. Min Act: -0.1700
Data Index: 6012658 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2374. Min Range: -5.2374
Max Act: 4.7374. Min Act: -0.1700
Data Index: 5296200 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2374. Min Range: -5.2374
Max Act: 4.7374. Min Act: -0.1700
Data Index: 332967 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19