Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 277 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1104. Min Range: -3.1104
Max Act: 3.1104. Min Act: -0.1700
Data Index: 2253565 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.9683. Min Act: -0.1700
Data Index: 3001902 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.9367. Min Act: -0.1700
Data Index: 6514296 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.9208. Min Act: -0.1700
Data Index: 7922431 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.9367. Min Act: -0.1700
Data Index: 1853147 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8891. Min Act: -0.1700
Data Index: 5837150 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.9050. Min Act: -0.1700
Data Index: 3690344 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.9050. Min Act: -0.1700
Data Index: 3327165 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8891. Min Act: -0.1700
Data Index: 5837151 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8891. Min Act: -0.1700
Data Index: 7782898 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8891. Min Act: -0.1700
Data Index: 5837145 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8732. Min Act: -0.1700
Data Index: 3327164 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8891. Min Act: -0.1700
Data Index: 4940502 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8574. Min Act: -0.1700
Data Index: 8286141 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8415. Min Act: -0.1700
Data Index: 4500675 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8415. Min Act: -0.1700
Data Index: 4099369 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8415. Min Act: -0.1700
Data Index: 1136832 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8256. Min Act: -0.1700
Data Index: 458052 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8097. Min Act: -0.1700
Data Index: 555349 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1104. Min Range: -3.1104
Max Act: 2.8097. Min Act: -0.1700
Data Index: 7401459 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19