Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2209 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0865. Min Range: -7.0865
Max Act: 7.0865. Min Act: -0.1700
Data Index: 6880256 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.9615. Min Act: -0.1700
Data Index: 1322130 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.8677. Min Act: -0.1700
Data Index: 5601672 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.8365. Min Act: -0.1700
Data Index: 5572999 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7740. Min Act: -0.1700
Data Index: 6400485 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7115. Min Act: -0.1700
Data Index: 2984437 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7115. Min Act: -0.1700
Data Index: 1357841 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7115. Min Act: -0.1700
Data Index: 3898521 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6802. Min Act: -0.1700
Data Index: 410049 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6490. Min Act: -0.1700
Data Index: 4841275 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6490. Min Act: -0.1700
Data Index: 7978375 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6490. Min Act: -0.1700
Data Index: 5703660 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6177. Min Act: -0.1700
Data Index: 4000535 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.5865. Min Act: -0.1700
Data Index: 8618572 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.5552. Min Act: -0.1700
Data Index: 5875864 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.5552. Min Act: -0.1700
Data Index: 7797310 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.5240. Min Act: -0.1700
Data Index: 2176959 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.5240. Min Act: -0.1700
Data Index: 2733319 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.5240. Min Act: -0.1700
Data Index: 8083730 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.4927. Min Act: -0.1700
Data Index: 6790574 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19