Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5038 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0474. Min Range: -7.0474
Max Act: 7.0474. Min Act: -0.1700
Data Index: 2797680 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.6724. Min Act: -0.1700
Data Index: 5686234 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.6412. Min Act: -0.1700
Data Index: 2455131 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.5162. Min Act: -0.1700
Data Index: 6020129 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.4849. Min Act: -0.1700
Data Index: 8084753 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.5162. Min Act: -0.1700
Data Index: 8036792 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.4537. Min Act: -0.1700
Data Index: 7573066 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.4537. Min Act: -0.1700
Data Index: 2409442 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.4537. Min Act: -0.1700
Data Index: 7813169 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.3912. Min Act: -0.1700
Data Index: 5262145 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.3287. Min Act: -0.1700
Data Index: 2384245 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.3599. Min Act: -0.1700
Data Index: 7813168 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.3599. Min Act: -0.1700
Data Index: 216965 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.3287. Min Act: -0.1700
Data Index: 272772 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.2974. Min Act: -0.1700
Data Index: 5920452 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.2974. Min Act: -0.1700
Data Index: 4375221 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.2974. Min Act: -0.1700
Data Index: 3712595 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.2974. Min Act: -0.1700
Data Index: 2984051 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.2662. Min Act: -0.1700
Data Index: 624128 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0474. Min Range: -7.0474
Max Act: 6.2662. Min Act: -0.1700
Data Index: 4920794 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19