Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3820 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.2697. Min Act: -0.1700
Data Index: 7264038 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.2697. Min Act: -0.1700
Data Index: 3933836 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.2367. Min Act: -0.1700
Data Index: 1684344 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.2035. Min Act: -0.1700
Data Index: 8487452 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1703. Min Act: -0.1700
Data Index: 684759 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1869. Min Act: -0.1700
Data Index: 6137370 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1869. Min Act: -0.1700
Data Index: 5897813 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1869. Min Act: -0.1700
Data Index: 8487455 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1703. Min Act: -0.1700
Data Index: 720957 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1703. Min Act: -0.1700
Data Index: 6023294 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1703. Min Act: -0.1700
Data Index: 5124743 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1703. Min Act: -0.1700
Data Index: 8352428 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1703. Min Act: -0.1700
Data Index: 4807582 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1370. Min Act: -0.1700
Data Index: 2391842 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1537. Min Act: -0.1700
Data Index: 5420529 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1203. Min Act: -0.1700
Data Index: 7426630 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1370. Min Act: -0.1700
Data Index: 7264040 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1370. Min Act: -0.1700
Data Index: 4436664 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1370. Min Act: -0.1700
Data Index: 5638303 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2697. Min Range: -2.2697
Max Act: 2.1036. Min Act: -0.1700
Data Index: 6053724 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19