Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3707. Min Range: -5.3707
Max Act: 5.3707. Min Act: -0.1700
Data Index: 4157932 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3707. Min Range: -5.3707
Max Act: 5.3707. Min Act: -0.1700
Data Index: 3467336 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3707. Min Range: -5.3707
Max Act: 5.2770. Min Act: -0.1700
Data Index: 870215 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3707. Min Range: -5.3707
Max Act: 5.0582. Min Act: -0.1700
Data Index: 4767100 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.9957. Min Act: -0.1700
Data Index: 4393714 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.9645. Min Act: -0.1700
Data Index: 5246986 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.9020. Min Act: -0.1700
Data Index: 654727 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.9020. Min Act: -0.1700
Data Index: 6457914 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.8395. Min Act: -0.1700
Data Index: 171750 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.8395. Min Act: -0.1700
Data Index: 8091271 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.8082. Min Act: -0.1700
Data Index: 6484278 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.8082. Min Act: -0.1700
Data Index: 5540864 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.8395. Min Act: -0.1700
Data Index: 6142386 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.8395. Min Act: -0.1700
Data Index: 4624548 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.8395. Min Act: -0.1700
Data Index: 6546184 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.7770. Min Act: -0.1700
Data Index: 666527 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.7457. Min Act: -0.1700
Data Index: 443655 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.7457. Min Act: -0.1700
Data Index: 3817024 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.7457. Min Act: -0.1700
Data Index: 4756192 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3707. Min Range: -5.3707
Max Act: 4.7457. Min Act: -0.1700
Data Index: 7152125 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19