Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.7056. Min Act: -0.1700
Data Index: 4143373 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.6119. Min Act: -0.1700
Data Index: 185399 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.6744. Min Act: -0.1700
Data Index: 5883014 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.6119. Min Act: -0.1700
Data Index: 1500116 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.5806. Min Act: -0.1700
Data Index: 7412639 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.5806. Min Act: -0.1700
Data Index: 3958759 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.5806. Min Act: -0.1700
Data Index: 442145 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.5806. Min Act: -0.1700
Data Index: 349626 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.5494. Min Act: -0.1700
Data Index: 761475 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.5494. Min Act: -0.1700
Data Index: 4041350 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.5181. Min Act: -0.1700
Data Index: 7736544 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.5181. Min Act: -0.1700
Data Index: 5571255 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.5494. Min Act: -0.1700
Data Index: 202664 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.4869. Min Act: -0.1700
Data Index: 4336653 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.5181. Min Act: -0.1700
Data Index: 5735993 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.4556. Min Act: -0.1700
Data Index: 8029209 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.4556. Min Act: -0.1700
Data Index: 2561921 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.4556. Min Act: -0.1700
Data Index: 1329293 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.4244. Min Act: -0.1700
Data Index: 6051515 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7056. Min Range: -5.7056
Max Act: 5.4244. Min Act: -0.1700
Data Index: 6699485 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19