Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6043 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2947. Min Act: -0.1700
Data Index: 456171 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2635. Min Act: -0.1700
Data Index: 2788449 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2635. Min Act: -0.1700
Data Index: 2992639 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2635. Min Act: -0.1700
Data Index: 2992636 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2635. Min Act: -0.1700
Data Index: 4326997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2635. Min Act: -0.1700
Data Index: 7121765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2635. Min Act: -0.1700
Data Index: 3263181 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2635. Min Act: -0.1700
Data Index: 3386196 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 3253392 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 4596584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 4468268 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 1788493 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 4199030 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 1559167 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 129281 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 27916 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 2992633 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 2439641 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 7512 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2322. Min Act: -0.1700
Data Index: 726137 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19