Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 839 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4710. Min Range: -7.4710
Max Act: 7.4710. Min Act: -0.1700
Data Index: 1032586 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4710. Min Range: -7.4710
Max Act: 7.1272. Min Act: -0.1700
Data Index: 8424649 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4710. Min Range: -7.4710
Max Act: 7.0335. Min Act: -0.1700
Data Index: 7831624 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.9085. Min Act: -0.1700
Data Index: 5614313 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.8772. Min Act: -0.1700
Data Index: 2974849 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.8460. Min Act: -0.1700
Data Index: 2323387 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.8147. Min Act: -0.1700
Data Index: 3336482 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.7522. Min Act: -0.1700
Data Index: 6476725 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.7210. Min Act: -0.1700
Data Index: 332038 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.6897. Min Act: -0.1700
Data Index: 7848654 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.6585. Min Act: -0.1700
Data Index: 5663535 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.6585. Min Act: -0.1700
Data Index: 719808 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.6585. Min Act: -0.1700
Data Index: 926686 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.6585. Min Act: -0.1700
Data Index: 2161004 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.6585. Min Act: -0.1700
Data Index: 6118344 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.6585. Min Act: -0.1700
Data Index: 5347224 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.6272. Min Act: -0.1700
Data Index: 8435441 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.6272. Min Act: -0.1700
Data Index: 4864324 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.5960. Min Act: -0.1700
Data Index: 4411260 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4710. Min Range: -7.4710
Max Act: 6.5960. Min Act: -0.1700
Data Index: 2461149 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19