Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3655 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.5235. Min Act: -0.1700
Data Index: 8301828 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.4922. Min Act: -0.1700
Data Index: 3756976 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.4610. Min Act: -0.1700
Data Index: 6638766 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.4297. Min Act: -0.1700
Data Index: 1727359 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.4610. Min Act: -0.1700
Data Index: 8821993 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.4297. Min Act: -0.1700
Data Index: 4454612 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3985. Min Act: -0.1700
Data Index: 3081409 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3985. Min Act: -0.1700
Data Index: 8280723 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.4297. Min Act: -0.1700
Data Index: 36211 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3672. Min Act: -0.1700
Data Index: 4367887 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3672. Min Act: -0.1700
Data Index: 1445786 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3672. Min Act: -0.1700
Data Index: 1063383 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3672. Min Act: -0.1700
Data Index: 2642403 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3672. Min Act: -0.1700
Data Index: 1818359 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3672. Min Act: -0.1700
Data Index: 6165254 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3360. Min Act: -0.1700
Data Index: 5340939 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3047. Min Act: -0.1700
Data Index: 3665695 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3672. Min Act: -0.1700
Data Index: 5358872 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3360. Min Act: -0.1700
Data Index: 5363843 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5235. Min Range: -4.5235
Max Act: 4.3360. Min Act: -0.1700
Data Index: 1190314 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19