Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4575 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0778. Min Range: -4.0778
Max Act: 4.0778. Min Act: -0.1700
Data Index: 1167819 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0778. Min Range: -4.0778
Max Act: 4.0466. Min Act: -0.1700
Data Index: 1341830 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0778. Min Range: -4.0778
Max Act: 4.0153. Min Act: -0.1700
Data Index: 3673380 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.9215. Min Act: -0.1700
Data Index: 5967719 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.9215. Min Act: -0.1700
Data Index: 8071164 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8903. Min Act: -0.1700
Data Index: 6653523 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8277. Min Act: -0.1700
Data Index: 7022821 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8277. Min Act: -0.1700
Data Index: 1205110 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8277. Min Act: -0.1700
Data Index: 7282044 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8277. Min Act: -0.1700
Data Index: 2654573 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8277. Min Act: -0.1700
Data Index: 5737507 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8277. Min Act: -0.1700
Data Index: 5660720 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8277. Min Act: -0.1700
Data Index: 5427397 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8277. Min Act: -0.1700
Data Index: 8736826 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7808. Min Act: -0.1700
Data Index: 8272398 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7652. Min Act: -0.1700
Data Index: 4107967 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7964. Min Act: -0.1700
Data Index: 4107964 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7652. Min Act: -0.1700
Data Index: 5967718 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7808. Min Act: -0.1700
Data Index: 3650187 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7652. Min Act: -0.1700
Data Index: 7746800 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19