Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1424 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1201. Min Range: -5.1201
Max Act: 5.1201. Min Act: -0.1700
Data Index: 8089924 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.7764. Min Act: -0.1700
Data Index: 2868171 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.7451. Min Act: -0.1700
Data Index: 3860551 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.7139. Min Act: -0.1700
Data Index: 1956642 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.6826. Min Act: -0.1700
Data Index: 4201072 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.6514. Min Act: -0.1700
Data Index: 2896201 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.6201. Min Act: -0.1700
Data Index: 5190584 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.6201. Min Act: -0.1700
Data Index: 1949751 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.5889. Min Act: -0.1700
Data Index: 5215408 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.5889. Min Act: -0.1700
Data Index: 7037605 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.5889. Min Act: -0.1700
Data Index: 185519 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.4951. Min Act: -0.1700
Data Index: 3668913 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.4951. Min Act: -0.1700
Data Index: 1617289 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.4639. Min Act: -0.1700
Data Index: 6953486 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.4951. Min Act: -0.1700
Data Index: 3037376 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.4951. Min Act: -0.1700
Data Index: 7073153 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.4639. Min Act: -0.1700
Data Index: 4271219 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.4639. Min Act: -0.1700
Data Index: 7750489 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.4639. Min Act: -0.1700
Data Index: 1012491 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1201. Min Range: -5.1201
Max Act: 4.4326. Min Act: -0.1700
Data Index: 495926 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19