Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5683 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.9544. Min Act: -0.1700
Data Index: 5027195 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8517. Min Act: -0.1700
Data Index: 8728488 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8348. Min Act: -0.1700
Data Index: 6336470 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8011. Min Act: -0.1700
Data Index: 3433580 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8179. Min Act: -0.1700
Data Index: 4813803 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8179. Min Act: -0.1700
Data Index: 1573021 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8179. Min Act: -0.1700
Data Index: 7995518 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8011. Min Act: -0.1700
Data Index: 6597082 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8011. Min Act: -0.1700
Data Index: 2452942 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8011. Min Act: -0.1700
Data Index: 8051622 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.7843. Min Act: -0.1700
Data Index: 305331 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8011. Min Act: -0.1700
Data Index: 1670401 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8011. Min Act: -0.1700
Data Index: 2713744 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8011. Min Act: -0.1700
Data Index: 1258649 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.8011. Min Act: -0.1700
Data Index: 2067540 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.7843. Min Act: -0.1700
Data Index: 3715107 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.7843. Min Act: -0.1700
Data Index: 1226851 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.7843. Min Act: -0.1700
Data Index: 3728530 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.7843. Min Act: -0.1700
Data Index: 3966517 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9544. Min Range: -0.9544
Max Act: 0.7843. Min Act: -0.1700
Data Index: 793790 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19