Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0960. Min Range: -5.0960
Max Act: 5.0960. Min Act: -0.1700
Data Index: 4875169 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0960. Min Range: -5.0960
Max Act: 5.0647. Min Act: -0.1700
Data Index: 1141985 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0960. Min Range: -5.0960
Max Act: 5.0335. Min Act: -0.1700
Data Index: 576575 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0960. Min Range: -5.0960
Max Act: 5.0335. Min Act: -0.1700
Data Index: 7998624 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0960. Min Range: -5.0960
Max Act: 5.0335. Min Act: -0.1700
Data Index: 3647822 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.7522. Min Act: -0.1700
Data Index: 3008584 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.6897. Min Act: -0.1700
Data Index: 988960 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.6897. Min Act: -0.1700
Data Index: 2552502 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.6897. Min Act: -0.1700
Data Index: 5340126 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.6585. Min Act: -0.1700
Data Index: 4796382 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.6272. Min Act: -0.1700
Data Index: 1623786 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.5960. Min Act: -0.1700
Data Index: 7117637 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.5647. Min Act: -0.1700
Data Index: 6191164 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.5335. Min Act: -0.1700
Data Index: 2552503 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.5335. Min Act: -0.1700
Data Index: 6284627 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.5335. Min Act: -0.1700
Data Index: 8166299 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.5335. Min Act: -0.1700
Data Index: 6400896 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.5022. Min Act: -0.1700
Data Index: 8647712 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.4710. Min Act: -0.1700
Data Index: 3297846 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0960. Min Range: -5.0960
Max Act: 4.4397. Min Act: -0.1700
Data Index: 1151986 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19