Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4474 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6789. Min Act: -0.1700
Data Index: 8108783 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6468. Min Act: -0.1700
Data Index: 5998178 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6307. Min Act: -0.1700
Data Index: 4719884 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6307. Min Act: -0.1700
Data Index: 8142418 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6307. Min Act: -0.1700
Data Index: 833283 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6147. Min Act: -0.1700
Data Index: 305860 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6147. Min Act: -0.1700
Data Index: 5761134 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.5986. Min Act: -0.1700
Data Index: 8299530 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6147. Min Act: -0.1700
Data Index: 3148208 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6147. Min Act: -0.1700
Data Index: 6289200 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6147. Min Act: -0.1700
Data Index: 8560385 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6147. Min Act: -0.1700
Data Index: 6266843 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.6147. Min Act: -0.1700
Data Index: 2445824 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.5986. Min Act: -0.1700
Data Index: 5551112 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.5825. Min Act: -0.1700
Data Index: 2909947 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.5825. Min Act: -0.1700
Data Index: 6014340 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.5986. Min Act: -0.1700
Data Index: 1284672 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.5986. Min Act: -0.1700
Data Index: 1000099 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.5825. Min Act: -0.1700
Data Index: 3029481 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6789. Min Range: -2.6789
Max Act: 2.5664. Min Act: -0.1700
Data Index: 4881886 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19