Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3860 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.4579. Min Act: -0.1700
Data Index: 2102455 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.4579. Min Act: -0.1700
Data Index: 3030873 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3642. Min Act: -0.1700
Data Index: 315430 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3642. Min Act: -0.1700
Data Index: 8194219 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3642. Min Act: -0.1700
Data Index: 1776131 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3329. Min Act: -0.1700
Data Index: 1825664 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3329. Min Act: -0.1700
Data Index: 2590528 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3017. Min Act: -0.1700
Data Index: 7382755 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3017. Min Act: -0.1700
Data Index: 6659845 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.3017. Min Act: -0.1700
Data Index: 315433 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2704. Min Act: -0.1700
Data Index: 1570181 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2392. Min Act: -0.1700
Data Index: 4548051 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2704. Min Act: -0.1700
Data Index: 6474230 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2704. Min Act: -0.1700
Data Index: 4733425 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2392. Min Act: -0.1700
Data Index: 7092953 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2392. Min Act: -0.1700
Data Index: 6771109 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2392. Min Act: -0.1700
Data Index: 8144098 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2079. Min Act: -0.1700
Data Index: 6659846 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2079. Min Act: -0.1700
Data Index: 5895492 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4579. Min Range: -4.4579
Max Act: 4.2392. Min Act: -0.1700
Data Index: 4210303 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19