Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3373. Min Range: -8.3373
Max Act: 8.3373. Min Act: -0.1700
Data Index: 405363 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3373. Min Range: -8.3373
Max Act: 8.0248. Min Act: -0.1700
Data Index: 1123488 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.8998. Min Act: -0.1700
Data Index: 5629881 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.8373. Min Act: -0.1700
Data Index: 3256779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.7748. Min Act: -0.1700
Data Index: 3829843 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.7123. Min Act: -0.1700
Data Index: 5629873 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.6498. Min Act: -0.1700
Data Index: 4726516 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.6186. Min Act: -0.1700
Data Index: 5333946 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.5561. Min Act: -0.1700
Data Index: 5582643 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.5561. Min Act: -0.1700
Data Index: 723184 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.5248. Min Act: -0.1700
Data Index: 846473 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.4936. Min Act: -0.1700
Data Index: 2417673 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.4936. Min Act: -0.1700
Data Index: 8381266 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.4311. Min Act: -0.1700
Data Index: 3256760 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.3686. Min Act: -0.1700
Data Index: 2842694 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.3686. Min Act: -0.1700
Data Index: 8161113 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.3373. Min Act: -0.1700
Data Index: 5856919 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.3373. Min Act: -0.1700
Data Index: 8189749 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.3686. Min Act: -0.1700
Data Index: 5847473 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3373. Min Range: -8.3373
Max Act: 7.3373. Min Act: -0.1700
Data Index: 1818219 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19