Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5908 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0865. Min Range: -6.0865
Max Act: 6.0865. Min Act: -0.1700
Data Index: 2797494 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0865. Min Range: -6.0865
Max Act: 6.0553. Min Act: -0.1700
Data Index: 6891114 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0865. Min Range: -6.0865
Max Act: 6.0553. Min Act: -0.1700
Data Index: 4009103 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0865. Min Range: -6.0865
Max Act: 6.0240. Min Act: -0.1700
Data Index: 5586420 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.9615. Min Act: -0.1700
Data Index: 2211182 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.9615. Min Act: -0.1700
Data Index: 7261641 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.9303. Min Act: -0.1700
Data Index: 3584144 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8990. Min Act: -0.1700
Data Index: 3823388 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.9303. Min Act: -0.1700
Data Index: 6891113 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8990. Min Act: -0.1700
Data Index: 7961710 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8678. Min Act: -0.1700
Data Index: 7333625 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8678. Min Act: -0.1700
Data Index: 8503852 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8678. Min Act: -0.1700
Data Index: 2864307 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8678. Min Act: -0.1700
Data Index: 3765366 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8678. Min Act: -0.1700
Data Index: 2757467 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8053. Min Act: -0.1700
Data Index: 2601156 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8365. Min Act: -0.1700
Data Index: 2808021 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8365. Min Act: -0.1700
Data Index: 8690439 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8365. Min Act: -0.1700
Data Index: 7550475 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0865. Min Range: -6.0865
Max Act: 5.8365. Min Act: -0.1700
Data Index: 634567 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19