Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1861 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1772. Min Range: -12.1772
Max Act: 12.1772. Min Act: -0.1700
Data Index: 4387955 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1772. Min Range: -12.1772
Max Act: 12.1147. Min Act: -0.1700
Data Index: 2920578 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1772. Min Range: -12.1772
Max Act: 11.8022. Min Act: -0.1700
Data Index: 4649964 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1772. Min Range: -12.1772
Max Act: 11.5522. Min Act: -0.1700
Data Index: 1084394 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1772. Min Range: -12.1772
Max Act: 11.5522. Min Act: -0.1700
Data Index: 5821230 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1772. Min Range: -12.1772
Max Act: 11.4897. Min Act: -0.1700
Data Index: 234480 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1772. Min Range: -12.1772
Max Act: 11.3647. Min Act: -0.1700
Data Index: 7599325 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1772. Min Range: -12.1772
Max Act: 11.2397. Min Act: -0.1700
Data Index: 6289101 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1772. Min Range: -12.1772
Max Act: 11.0522. Min Act: -0.1700
Data Index: 33135 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1772. Min Range: -12.1772
Max Act: 11.0522. Min Act: -0.1700
Data Index: 2551185 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1772. Min Range: -12.1772
Max Act: 10.9897. Min Act: -0.1700
Data Index: 565503 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1772. Min Range: -12.1772
Max Act: 10.9897. Min Act: -0.1700
Data Index: 1158570 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1772. Min Range: -12.1772
Max Act: 10.9897. Min Act: -0.1700
Data Index: 4945098 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1772. Min Range: -12.1772
Max Act: 10.9272. Min Act: -0.1700
Data Index: 3853544 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1772. Min Range: -12.1772
Max Act: 10.9272. Min Act: -0.1700
Data Index: 6752020 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1772. Min Range: -12.1772
Max Act: 10.9272. Min Act: -0.1700
Data Index: 4387976 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1772. Min Range: -12.1772
Max Act: 10.9272. Min Act: -0.1700
Data Index: 5151020 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1772. Min Range: -12.1772
Max Act: 10.9272. Min Act: -0.1700
Data Index: 2722316 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1772. Min Range: -12.1772
Max Act: 10.8647. Min Act: -0.1700
Data Index: 481032 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1772. Min Range: -12.1772
Max Act: 10.8647. Min Act: -0.1700
Data Index: 4945104 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19