Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2041 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4052. Min Range: -7.4052
Max Act: 7.4052. Min Act: -0.1700
Data Index: 6746641 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4052. Min Range: -7.4052
Max Act: 7.3427. Min Act: -0.1700
Data Index: 7177222 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.9052. Min Act: -0.1700
Data Index: 1671021 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.9052. Min Act: -0.1700
Data Index: 6555955 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.9052. Min Act: -0.1700
Data Index: 3281709 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.8427. Min Act: -0.1700
Data Index: 6768657 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.8427. Min Act: -0.1700
Data Index: 1573626 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.8115. Min Act: -0.1700
Data Index: 758841 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.7490. Min Act: -0.1700
Data Index: 6842430 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.6865. Min Act: -0.1698
Data Index: 2810545 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.7177. Min Act: -0.1700
Data Index: 6724892 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.6865. Min Act: -0.1700
Data Index: 811764 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.6552. Min Act: -0.1700
Data Index: 3542955 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.6552. Min Act: -0.1700
Data Index: 4400950 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.6552. Min Act: -0.1700
Data Index: 5882348 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.6240. Min Act: -0.1700
Data Index: 4611127 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.5927. Min Act: -0.1700
Data Index: 3945974 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.5615. Min Act: -0.1700
Data Index: 6963165 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.5615. Min Act: -0.1700
Data Index: 6061561 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4052. Min Range: -7.4052
Max Act: 6.5615. Min Act: -0.1700
Data Index: 502545 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19