Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3414 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.3336. Min Act: -0.1700
Data Index: 6405227 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.3024. Min Act: -0.1700
Data Index: 3865996 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.1773. Min Act: -0.1700
Data Index: 3865995 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.1461. Min Act: -0.1700
Data Index: 945645 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.1461. Min Act: -0.1700
Data Index: 3341259 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.1148. Min Act: -0.1700
Data Index: 5677862 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.0836. Min Act: -0.1700
Data Index: 2809304 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.0836. Min Act: -0.1700
Data Index: 686055 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.0836. Min Act: -0.1700
Data Index: 2438288 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.0523. Min Act: -0.1700
Data Index: 2726200 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.0523. Min Act: -0.1700
Data Index: 6491546 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.0523. Min Act: -0.1700
Data Index: 3593090 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.0211. Min Act: -0.1700
Data Index: 5140115 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.0211. Min Act: -0.1700
Data Index: 4747852 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3336. Min Range: -4.3336
Max Act: 4.0211. Min Act: -0.1700
Data Index: 4000272 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3336. Min Range: -4.3336
Max Act: 3.9898. Min Act: -0.1700
Data Index: 5169196 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3336. Min Range: -4.3336
Max Act: 3.9898. Min Act: -0.1700
Data Index: 3593087 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3336. Min Range: -4.3336
Max Act: 3.9898. Min Act: -0.1700
Data Index: 5870360 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3336. Min Range: -4.3336
Max Act: 3.9898. Min Act: -0.1700
Data Index: 4583676 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3336. Min Range: -4.3336
Max Act: 3.9898. Min Act: -0.1700
Data Index: 161250 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19