Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 521 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1691. Min Range: -6.1691
Max Act: 6.1691. Min Act: -0.1700
Data Index: 6132205 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1691. Min Range: -6.1691
Max Act: 6.1378. Min Act: -0.1700
Data Index: 6374427 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1691. Min Range: -6.1691
Max Act: 6.1066. Min Act: -0.1700
Data Index: 8598199 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1691. Min Range: -6.1691
Max Act: 6.0753. Min Act: -0.1700
Data Index: 4146711 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1691. Min Range: -6.1691
Max Act: 6.0441. Min Act: -0.1700
Data Index: 4565003 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1691. Min Range: -6.1691
Max Act: 6.0128. Min Act: -0.1700
Data Index: 5023307 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1691. Min Range: -6.1691
Max Act: 6.0441. Min Act: -0.1700
Data Index: 5511802 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1691. Min Range: -6.1691
Max Act: 6.0128. Min Act: -0.1700
Data Index: 1363666 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.9816. Min Act: -0.1700
Data Index: 922188 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.9503. Min Act: -0.1700
Data Index: 282812 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.9503. Min Act: -0.1700
Data Index: 5653310 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.9191. Min Act: -0.1700
Data Index: 876514 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.8878. Min Act: -0.1700
Data Index: 4828393 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.8878. Min Act: -0.1700
Data Index: 679457 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.8566. Min Act: -0.1700
Data Index: 4703722 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.7941. Min Act: -0.1700
Data Index: 4927608 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.8253. Min Act: -0.1700
Data Index: 6179383 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.8253. Min Act: -0.1700
Data Index: 7312457 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.8253. Min Act: -0.1700
Data Index: 3731948 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1691. Min Range: -6.1691
Max Act: 5.8253. Min Act: -0.1700
Data Index: 7042362 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19