Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4498 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.6293. Min Act: -0.1700
Data Index: 7707221 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.5649. Min Act: -0.1700
Data Index: 4418073 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.5164. Min Act: -0.1700
Data Index: 6036889 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.5003. Min Act: -0.1700
Data Index: 7160621 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.4678. Min Act: -0.1700
Data Index: 731274 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.4516. Min Act: -0.1700
Data Index: 952073 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.4678. Min Act: -0.1700
Data Index: 3472108 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.4840. Min Act: -0.1700
Data Index: 8664550 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.4516. Min Act: -0.1700
Data Index: 53445 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.4840. Min Act: -0.1700
Data Index: 1635318 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.4516. Min Act: -0.1700
Data Index: 5511102 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.4353. Min Act: -0.1700
Data Index: 4264410 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.4027. Min Act: -0.1700
Data Index: 4297871 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.3700. Min Act: -0.1700
Data Index: 1356920 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.3537. Min Act: -0.1700
Data Index: 5494089 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.3537. Min Act: -0.1700
Data Index: 1723213 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.3537. Min Act: -0.1700
Data Index: 6520376 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.3537. Min Act: -0.1700
Data Index: 116122 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.3537. Min Act: -0.1700
Data Index: 6159117 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6293. Min Range: -2.6293
Max Act: 2.3537. Min Act: -0.1700
Data Index: 4421544 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19