Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 683 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.2551. Min Act: -0.1700
Data Index: 5785448 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.1926. Min Act: -0.1700
Data Index: 7584218 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.2238. Min Act: -0.1700
Data Index: 1049786 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.1926. Min Act: -0.1700
Data Index: 523270 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.1613. Min Act: -0.1700
Data Index: 8617303 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.1613. Min Act: -0.1700
Data Index: 3385776 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.1301. Min Act: -0.1700
Data Index: 2312413 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.1301. Min Act: -0.1700
Data Index: 4927626 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.1301. Min Act: -0.1700
Data Index: 787912 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0675. Min Act: -0.1700
Data Index: 2147036 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0675. Min Act: -0.1700
Data Index: 1222283 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0675. Min Act: -0.1700
Data Index: 692135 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0675. Min Act: -0.1700
Data Index: 433807 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0675. Min Act: -0.1700
Data Index: 6955269 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0363. Min Act: -0.1700
Data Index: 6787515 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0675. Min Act: -0.1700
Data Index: 6569326 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0675. Min Act: -0.1700
Data Index: 6004424 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0675. Min Act: -0.1700
Data Index: 2073455 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0675. Min Act: -0.1700
Data Index: 4861249 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2551. Min Range: -4.2551
Max Act: 4.0675. Min Act: -0.1700
Data Index: 4108650 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19