Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1630 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4629. Min Range: -6.4629
Max Act: 6.4629. Min Act: -0.1700
Data Index: 3061408 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4629. Min Range: -6.4629
Max Act: 6.3692. Min Act: -0.1700
Data Index: 1373841 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4629. Min Range: -6.4629
Max Act: 6.2129. Min Act: -0.1700
Data Index: 5832241 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4629. Min Range: -6.4629
Max Act: 6.1192. Min Act: -0.1700
Data Index: 140701 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4629. Min Range: -6.4629
Max Act: 6.1504. Min Act: -0.1700
Data Index: 7471024 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4629. Min Range: -6.4629
Max Act: 6.0567. Min Act: -0.1700
Data Index: 836735 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4629. Min Range: -6.4629
Max Act: 6.0567. Min Act: -0.1700
Data Index: 5912760 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.9942. Min Act: -0.1700
Data Index: 8670169 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.9942. Min Act: -0.1700
Data Index: 5143933 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.9629. Min Act: -0.1700
Data Index: 2347083 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.9629. Min Act: -0.1700
Data Index: 8626343 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.9317. Min Act: -0.1700
Data Index: 5312719 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.9004. Min Act: -0.1700
Data Index: 7663454 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.9317. Min Act: -0.1700
Data Index: 4968157 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.9004. Min Act: -0.1700
Data Index: 2101277 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.8692. Min Act: -0.1700
Data Index: 5944113 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.9317. Min Act: -0.1700
Data Index: 7370941 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.8692. Min Act: -0.1700
Data Index: 1164903 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.9004. Min Act: -0.1700
Data Index: 2969902 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4629. Min Range: -6.4629
Max Act: 5.8692. Min Act: -0.1700
Data Index: 8158275 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19