Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 300 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1530. Min Range: -6.1530
Max Act: 6.1530. Min Act: -0.1700
Data Index: 1183401 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1530. Min Range: -6.1530
Max Act: 6.0280. Min Act: -0.1700
Data Index: 39594 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.9967. Min Act: -0.1700
Data Index: 3861164 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.9967. Min Act: -0.1700
Data Index: 4500056 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.9655. Min Act: -0.1700
Data Index: 6631392 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.9655. Min Act: -0.1700
Data Index: 4783092 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.9655. Min Act: -0.1700
Data Index: 396733 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.9030. Min Act: -0.1700
Data Index: 7080727 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.8717. Min Act: -0.1700
Data Index: 6884833 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.8717. Min Act: -0.1700
Data Index: 5743685 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.8405. Min Act: -0.1700
Data Index: 6552111 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.8092. Min Act: -0.1700
Data Index: 1004617 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.7467. Min Act: -0.1700
Data Index: 6701724 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.7780. Min Act: -0.1700
Data Index: 7591550 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.7780. Min Act: -0.1700
Data Index: 751920 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.7155. Min Act: -0.1700
Data Index: 5225409 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.7155. Min Act: -0.1700
Data Index: 8555490 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.6842. Min Act: -0.1700
Data Index: 7488461 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.6842. Min Act: -0.1700
Data Index: 5759408 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1530. Min Range: -6.1530
Max Act: 5.6530. Min Act: -0.1700
Data Index: 2738149 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19