Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1765 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.7935. Min Act: -0.1700
Data Index: 1277383 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.5123. Min Act: -0.1700
Data Index: 3559265 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.5123. Min Act: -0.1700
Data Index: 7130712 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4810. Min Act: -0.1700
Data Index: 3789301 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4185. Min Act: -0.1700
Data Index: 512931 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4185. Min Act: -0.1700
Data Index: 1747530 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4498. Min Act: -0.1700
Data Index: 8247056 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4185. Min Act: -0.1700
Data Index: 1814667 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.3873. Min Act: -0.1700
Data Index: 8045163 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4185. Min Act: -0.1700
Data Index: 1531495 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.3873. Min Act: -0.1700
Data Index: 1252668 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.4185. Min Act: -0.1700
Data Index: 3638844 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.3873. Min Act: -0.1700
Data Index: 3224493 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.3560. Min Act: -0.1700
Data Index: 5389287 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.3560. Min Act: -0.1700
Data Index: 6879606 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.3560. Min Act: -0.1700
Data Index: 661110 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.2935. Min Act: -0.1700
Data Index: 5840618 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.3248. Min Act: -0.1700
Data Index: 8055999 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.2310. Min Act: -0.1700
Data Index: 1693943 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.2623. Min Act: -0.1700
Data Index: 5460906 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19