Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2408 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0933. Min Range: -6.0933
Max Act: 6.0933. Min Act: -0.1700
Data Index: 858903 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0933. Min Range: -6.0933
Max Act: 6.0621. Min Act: -0.1700
Data Index: 427825 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8433. Min Act: -0.1700
Data Index: 8789402 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8121. Min Act: -0.1700
Data Index: 1629463 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.8121. Min Act: -0.1700
Data Index: 6187846 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.7808. Min Act: -0.1700
Data Index: 7326481 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.7808. Min Act: -0.1700
Data Index: 6410406 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.7808. Min Act: -0.1700
Data Index: 6149533 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.7183. Min Act: -0.1700
Data Index: 8488322 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.7183. Min Act: -0.1700
Data Index: 2315993 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.7183. Min Act: -0.1700
Data Index: 4127889 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.6871. Min Act: -0.1700
Data Index: 4913329 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.6871. Min Act: -0.1700
Data Index: 7961596 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.6871. Min Act: -0.1700
Data Index: 524947 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.6871. Min Act: -0.1700
Data Index: 4668435 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.6246. Min Act: -0.1700
Data Index: 1895528 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.6558. Min Act: -0.1700
Data Index: 8348731 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.6558. Min Act: -0.1700
Data Index: 4729253 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.6558. Min Act: -0.1700
Data Index: 4415600 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0933. Min Range: -6.0933
Max Act: 5.6558. Min Act: -0.1700
Data Index: 1494797 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19