Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 428 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.4988. Min Act: -0.1700
Data Index: 8692322 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.4363. Min Act: -0.1700
Data Index: 4196455 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.4051. Min Act: -0.1700
Data Index: 4278729 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.4051. Min Act: -0.1700
Data Index: 4493073 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.4051. Min Act: -0.1700
Data Index: 1531193 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.3426. Min Act: -0.1700
Data Index: 4179717 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.3426. Min Act: -0.1700
Data Index: 7720092 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.3113. Min Act: -0.1700
Data Index: 6248099 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.3113. Min Act: -0.1700
Data Index: 1603040 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.2801. Min Act: -0.1700
Data Index: 7848103 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.2488. Min Act: -0.1700
Data Index: 5944324 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.2488. Min Act: -0.1700
Data Index: 4812928 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.2488. Min Act: -0.1700
Data Index: 6884266 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.2176. Min Act: -0.1700
Data Index: 250568 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.2176. Min Act: -0.1700
Data Index: 1537225 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.2176. Min Act: -0.1700
Data Index: 7639659 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.1863. Min Act: -0.1700
Data Index: 4769598 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.2176. Min Act: -0.1700
Data Index: 4620057 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.2176. Min Act: -0.1700
Data Index: 7845529 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4988. Min Range: -5.4988
Max Act: 5.2176. Min Act: -0.1700
Data Index: 65410 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19