Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.7708. Min Act: -0.1700
Data Index: 6238881 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.3637. Min Act: -0.1700
Data Index: 6462063 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.3167. Min Act: -0.1700
Data Index: 8209409 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.2696. Min Act: -0.1700
Data Index: 586683 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.2067. Min Act: -0.1700
Data Index: 1751361 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.2224. Min Act: -0.1700
Data Index: 1112926 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.2067. Min Act: -0.1700
Data Index: 6119214 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1752. Min Act: -0.1700
Data Index: 7391080 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1752. Min Act: -0.1700
Data Index: 3357997 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1595. Min Act: -0.1700
Data Index: 3347771 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1438. Min Act: -0.1700
Data Index: 1098535 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1438. Min Act: -0.1700
Data Index: 2875904 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1438. Min Act: -0.1700
Data Index: 1298050 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1595. Min Act: -0.1700
Data Index: 1982151 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1438. Min Act: -0.1700
Data Index: 1351023 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1280. Min Act: -0.1700
Data Index: 4160520 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1280. Min Act: -0.1700
Data Index: 7065089 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1280. Min Act: -0.1700
Data Index: 3183505 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1123. Min Act: -0.1700
Data Index: 4902304 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7708. Min Range: -3.7708
Max Act: 3.1280. Min Act: -0.1700
Data Index: 298122 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19