Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4978. Min Range: -6.4978
Max Act: 6.4978. Min Act: -0.1700
Data Index: 1290319 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4978. Min Range: -6.4978
Max Act: 6.4353. Min Act: -0.1700
Data Index: 1983025 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4978. Min Range: -6.4978
Max Act: 6.2790. Min Act: -0.1700
Data Index: 1385276 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4978. Min Range: -6.4978
Max Act: 6.2165. Min Act: -0.1700
Data Index: 1936548 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4978. Min Range: -6.4978
Max Act: 6.1228. Min Act: -0.1700
Data Index: 3514505 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4978. Min Range: -6.4978
Max Act: 6.1228. Min Act: -0.1700
Data Index: 6852090 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4978. Min Range: -6.4978
Max Act: 6.1540. Min Act: -0.1700
Data Index: 2917186 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4978. Min Range: -6.4978
Max Act: 6.0915. Min Act: -0.1700
Data Index: 6917568 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4978. Min Range: -6.4978
Max Act: 6.0603. Min Act: -0.1700
Data Index: 899832 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4978. Min Range: -6.4978
Max Act: 6.0603. Min Act: -0.1700
Data Index: 7789587 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4978. Min Range: -6.4978
Max Act: 5.9978. Min Act: -0.1700
Data Index: 498302 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4978. Min Range: -6.4978
Max Act: 5.9978. Min Act: -0.1700
Data Index: 1150466 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4978. Min Range: -6.4978
Max Act: 5.9665. Min Act: -0.1700
Data Index: 3455351 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4978. Min Range: -6.4978
Max Act: 5.9665. Min Act: -0.1700
Data Index: 3183506 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4978. Min Range: -6.4978
Max Act: 5.9665. Min Act: -0.1700
Data Index: 461599 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4978. Min Range: -6.4978
Max Act: 5.9353. Min Act: -0.1700
Data Index: 8117012 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4978. Min Range: -6.4978
Max Act: 5.9353. Min Act: -0.1700
Data Index: 7821089 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4978. Min Range: -6.4978
Max Act: 5.8415. Min Act: -0.1700
Data Index: 5442128 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4978. Min Range: -6.4978
Max Act: 5.8415. Min Act: -0.1700
Data Index: 2937248 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4978. Min Range: -6.4978
Max Act: 5.8415. Min Act: -0.1700
Data Index: 494186 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19