Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5860. Min Range: -6.5860
Max Act: 6.5860. Min Act: -0.1700
Data Index: 1917326 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5860. Min Range: -6.5860
Max Act: 6.3047. Min Act: -0.1700
Data Index: 2481880 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5860. Min Range: -6.5860
Max Act: 6.2735. Min Act: -0.1700
Data Index: 8531303 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5860. Min Range: -6.5860
Max Act: 6.1485. Min Act: -0.1700
Data Index: 6738419 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5860. Min Range: -6.5860
Max Act: 6.1797. Min Act: -0.1700
Data Index: 8531302 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.7110. Min Act: -0.1700
Data Index: 3008216 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.6485. Min Act: -0.1700
Data Index: 2295517 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.5860. Min Act: -0.1700
Data Index: 4886829 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.5547. Min Act: -0.1700
Data Index: 3542542 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.5547. Min Act: -0.1700
Data Index: 2551596 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.4922. Min Act: -0.1700
Data Index: 8243987 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.5235. Min Act: -0.1700
Data Index: 3495345 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.4610. Min Act: -0.1700
Data Index: 2486858 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.4922. Min Act: -0.1700
Data Index: 8243986 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.4297. Min Act: -0.1700
Data Index: 2977440 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.4297. Min Act: -0.1700
Data Index: 3620627 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.3985. Min Act: -0.1700
Data Index: 718403 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.3672. Min Act: -0.1700
Data Index: 7172485 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.3672. Min Act: -0.1700
Data Index: 7034437 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5860. Min Range: -6.5860
Max Act: 5.3360. Min Act: -0.1700
Data Index: 6398693 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19