Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1418 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2234. Min Range: -7.2234
Max Act: 7.2234. Min Act: -0.1700
Data Index: 5707249 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2234. Min Range: -7.2234
Max Act: 7.1921. Min Act: -0.1700
Data Index: 8713486 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2234. Min Range: -7.2234
Max Act: 7.0984. Min Act: -0.1700
Data Index: 4775569 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2234. Min Range: -7.2234
Max Act: 7.0984. Min Act: -0.1700
Data Index: 6773386 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2234. Min Range: -7.2234
Max Act: 7.0671. Min Act: -0.1700
Data Index: 3670650 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2234. Min Range: -7.2234
Max Act: 7.0046. Min Act: -0.1700
Data Index: 8395542 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2234. Min Range: -7.2234
Max Act: 7.0046. Min Act: -0.1700
Data Index: 7513100 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2234. Min Range: -7.2234
Max Act: 7.0046. Min Act: -0.1700
Data Index: 5027960 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2234. Min Range: -7.2234
Max Act: 7.0046. Min Act: -0.1700
Data Index: 724902 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.9421. Min Act: -0.1700
Data Index: 4006135 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.8796. Min Act: -0.1700
Data Index: 3431934 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.8484. Min Act: -0.1700
Data Index: 8565346 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.8171. Min Act: -0.1700
Data Index: 7670501 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.8171. Min Act: -0.1700
Data Index: 8646505 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.8171. Min Act: -0.1700
Data Index: 8495308 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.7546. Min Act: -0.1700
Data Index: 2262666 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.6921. Min Act: -0.1700
Data Index: 453537 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.7234. Min Act: -0.1700
Data Index: 4896992 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.6921. Min Act: -0.1700
Data Index: 667564 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2234. Min Range: -7.2234
Max Act: 6.6921. Min Act: -0.1700
Data Index: 8374696 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19