Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.8522. Min Act: -0.1700
Data Index: 6376532 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.8210. Min Act: -0.1700
Data Index: 4794719 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.8210. Min Act: -0.1700
Data Index: 5625783 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.7897. Min Act: -0.1700
Data Index: 3377993 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.8210. Min Act: -0.1700
Data Index: 7487273 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.7272. Min Act: -0.1700
Data Index: 3198877 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.6960. Min Act: -0.1700
Data Index: 6474250 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.6335. Min Act: -0.1700
Data Index: 6141710 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.6335. Min Act: -0.1700
Data Index: 4794720 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.6647. Min Act: -0.1700
Data Index: 3612920 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.6647. Min Act: -0.1700
Data Index: 5202885 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.6335. Min Act: -0.1700
Data Index: 2301776 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.6022. Min Act: -0.1700
Data Index: 4703611 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.6022. Min Act: -0.1700
Data Index: 4703612 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.6022. Min Act: -0.1700
Data Index: 1542572 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.6335. Min Act: -0.1700
Data Index: 714593 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.5397. Min Act: -0.1700
Data Index: 5198230 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.5710. Min Act: -0.1700
Data Index: 6143055 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.5710. Min Act: -0.1700
Data Index: 5152546 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8522. Min Range: -6.8522
Max Act: 6.5085. Min Act: -0.1700
Data Index: 3252588 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19