Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.3686. Min Act: -0.1700
Data Index: 2126283 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.3686. Min Act: -0.1700
Data Index: 5023610 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.3374. Min Act: -0.1700
Data Index: 6931848 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.3686. Min Act: -0.1700
Data Index: 189539 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.3061. Min Act: -0.1700
Data Index: 6115739 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.3061. Min Act: -0.1700
Data Index: 7924669 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.2749. Min Act: -0.1700
Data Index: 50524 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.2749. Min Act: -0.1700
Data Index: 3190418 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.2436. Min Act: -0.1700
Data Index: 457659 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.2436. Min Act: -0.1700
Data Index: 1354098 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.2124. Min Act: -0.1700
Data Index: 7134449 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.1499. Min Act: -0.1700
Data Index: 7997022 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.1499. Min Act: -0.1700
Data Index: 5876089 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.1811. Min Act: -0.1700
Data Index: 2607976 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.1186. Min Act: -0.1700
Data Index: 3617739 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.0874. Min Act: -0.1700
Data Index: 2985123 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.1186. Min Act: -0.1700
Data Index: 6028018 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.1186. Min Act: -0.1700
Data Index: 4978826 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.0874. Min Act: -0.1700
Data Index: 1168301 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3686. Min Range: -5.3686
Max Act: 5.0561. Min Act: -0.1700
Data Index: 6009846 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19