Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6372 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.6873. Min Act: -0.1700
Data Index: 55682 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.3748. Min Act: -0.1700
Data Index: 5500551 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.3436. Min Act: -0.1700
Data Index: 6075371 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.3123. Min Act: -0.1700
Data Index: 3746316 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.2811. Min Act: -0.1700
Data Index: 5849336 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.2186. Min Act: -0.1700
Data Index: 5719146 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.2186. Min Act: -0.1700
Data Index: 7755281 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.1873. Min Act: -0.1700
Data Index: 7056687 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.1561. Min Act: -0.1700
Data Index: 718817 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.1561. Min Act: -0.1700
Data Index: 8006743 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.1561. Min Act: -0.1700
Data Index: 7673582 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.1561. Min Act: -0.1700
Data Index: 3779565 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.0936. Min Act: -0.1700
Data Index: 5569056 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.1248. Min Act: -0.1700
Data Index: 7304670 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.0936. Min Act: -0.1700
Data Index: 3985325 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.0623. Min Act: -0.1700
Data Index: 4616505 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.0936. Min Act: -0.1700
Data Index: 6253783 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.0623. Min Act: -0.1700
Data Index: 4927436 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.0311. Min Act: -0.1700
Data Index: 6269978 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6873. Min Range: -7.6873
Max Act: 7.0311. Min Act: -0.1700
Data Index: 4883294 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19