Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1100 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1446. Min Range: -6.1446
Max Act: 6.1446. Min Act: -0.1700
Data Index: 1319 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1446. Min Range: -6.1446
Max Act: 6.1134. Min Act: -0.1700
Data Index: 2326900 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1446. Min Range: -6.1446
Max Act: 6.0821. Min Act: -0.1700
Data Index: 3485217 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1446. Min Range: -6.1446
Max Act: 6.0196. Min Act: -0.1700
Data Index: 4226074 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.9259. Min Act: -0.1700
Data Index: 8157466 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8946. Min Act: -0.1700
Data Index: 8779229 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8946. Min Act: -0.1700
Data Index: 4041067 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8946. Min Act: -0.1700
Data Index: 1889893 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8946. Min Act: -0.1700
Data Index: 1755756 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8946. Min Act: -0.1700
Data Index: 4377869 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8634. Min Act: -0.1700
Data Index: 5385397 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8634. Min Act: -0.1700
Data Index: 5798949 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8634. Min Act: -0.1700
Data Index: 1324908 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8321. Min Act: -0.1700
Data Index: 6637473 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8009. Min Act: -0.1700
Data Index: 2448925 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8009. Min Act: -0.1700
Data Index: 5369611 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.7696. Min Act: -0.1700
Data Index: 5214346 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.7696. Min Act: -0.1700
Data Index: 8284582 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.8009. Min Act: -0.1700
Data Index: 6667577 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1446. Min Range: -6.1446
Max Act: 5.7696. Min Act: -0.1700
Data Index: 7042373 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19