Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4789 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.6326. Min Act: -0.1700
Data Index: 647570 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.2576. Min Act: -0.1700
Data Index: 48445 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.2263. Min Act: -0.1700
Data Index: 1133293 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1951. Min Act: -0.1700
Data Index: 5469806 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1951. Min Act: -0.1700
Data Index: 3145829 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1951. Min Act: -0.1700
Data Index: 5819721 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1638. Min Act: -0.1700
Data Index: 5524455 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1638. Min Act: -0.1700
Data Index: 5410140 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1326. Min Act: -0.1700
Data Index: 4328003 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1326. Min Act: -0.1700
Data Index: 3140213 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1013. Min Act: -0.1700
Data Index: 4311113 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1013. Min Act: -0.1700
Data Index: 7228229 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1013. Min Act: -0.1700
Data Index: 2812182 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1013. Min Act: -0.1700
Data Index: 4517474 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1013. Min Act: -0.1700
Data Index: 4698950 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1326. Min Act: -0.1700
Data Index: 3085179 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1013. Min Act: -0.1700
Data Index: 3038822 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1013. Min Act: -0.1700
Data Index: 3536945 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1013. Min Act: -0.1700
Data Index: 26782 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6326. Min Range: -6.6326
Max Act: 6.1013. Min Act: -0.1700
Data Index: 131531 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19