Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.5185. Min Act: -0.1700
Data Index: 3560304 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.3935. Min Act: -0.1700
Data Index: 6069857 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.3935. Min Act: -0.1700
Data Index: 537418 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.3310. Min Act: -0.1700
Data Index: 8379925 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.3310. Min Act: -0.1700
Data Index: 2889045 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.2685. Min Act: -0.1700
Data Index: 6543659 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.2060. Min Act: -0.1700
Data Index: 7273130 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.2060. Min Act: -0.1700
Data Index: 3343685 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.2060. Min Act: -0.1700
Data Index: 3794444 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.1747. Min Act: -0.1700
Data Index: 1243547 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.1122. Min Act: -0.1700
Data Index: 4434356 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.1122. Min Act: -0.1700
Data Index: 3046566 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.1122. Min Act: -0.1700
Data Index: 870384 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.0810. Min Act: -0.1700
Data Index: 3267446 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.0497. Min Act: -0.1700
Data Index: 5884594 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5185. Min Range: -6.5185
Max Act: 5.9872. Min Act: -0.1700
Data Index: 3485751 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.0185. Min Act: -0.1700
Data Index: 38633 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.0185. Min Act: -0.1700
Data Index: 7657139 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.0185. Min Act: -0.1700
Data Index: 3706018 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5185. Min Range: -6.5185
Max Act: 6.0185. Min Act: -0.1700
Data Index: 7976311 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19