Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2493 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.6044. Min Act: -0.1700
Data Index: 5633837 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.5419. Min Act: -0.1700
Data Index: 1677821 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.4482. Min Act: -0.1700
Data Index: 8230547 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.4169. Min Act: -0.1700
Data Index: 2388865 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.3544. Min Act: -0.1700
Data Index: 7604470 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.2919. Min Act: -0.1700
Data Index: 5571592 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.2294. Min Act: -0.1700
Data Index: 72990 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.2294. Min Act: -0.1700
Data Index: 4116387 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.1357. Min Act: -0.1700
Data Index: 1363538 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.1044. Min Act: -0.1700
Data Index: 2487810 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.1044. Min Act: -0.1700
Data Index: 8127497 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.1044. Min Act: -0.1700
Data Index: 4987278 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.1044. Min Act: -0.1700
Data Index: 3967898 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.0732. Min Act: -0.1700
Data Index: 7961834 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.1044. Min Act: -0.1700
Data Index: 3667025 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.0732. Min Act: -0.1700
Data Index: 701242 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.0732. Min Act: -0.1700
Data Index: 4119148 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.0419. Min Act: -0.1700
Data Index: 3771733 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.0732. Min Act: -0.1700
Data Index: 3255030 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6044. Min Range: -6.6044
Max Act: 6.0419. Min Act: -0.1700
Data Index: 506059 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19