Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.8716. Min Act: -0.1700
Data Index: 1825266 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.4654. Min Act: -0.1700
Data Index: 4304719 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.4341. Min Act: -0.1700
Data Index: 5179364 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.4341. Min Act: -0.1700
Data Index: 3461307 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.4029. Min Act: -0.1700
Data Index: 3779034 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.4029. Min Act: -0.1700
Data Index: 4029341 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.4029. Min Act: -0.1700
Data Index: 787278 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3091. Min Act: -0.1700
Data Index: 725310 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3403. Min Act: -0.1700
Data Index: 6199833 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3403. Min Act: -0.1700
Data Index: 5091829 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3091. Min Act: -0.1700
Data Index: 6202788 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3403. Min Act: -0.1700
Data Index: 502228 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3091. Min Act: -0.1700
Data Index: 7103552 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3091. Min Act: -0.1700
Data Index: 6021604 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3091. Min Act: -0.1700
Data Index: 7895874 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3091. Min Act: -0.1700
Data Index: 1105069 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.2778. Min Act: -0.1700
Data Index: 8310486 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.2778. Min Act: -0.1700
Data Index: 4846304 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3091. Min Act: -0.1700
Data Index: 1497115 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8716. Min Range: -4.8716
Max Act: 4.3091. Min Act: -0.1700
Data Index: 1767507 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19