Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0338. Min Range: -6.0338
Max Act: 6.0338. Min Act: -0.1700
Data Index: 3926589 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.8150. Min Act: -0.1700
Data Index: 3034228 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.7525. Min Act: -0.1700
Data Index: 2938831 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.6275. Min Act: -0.1700
Data Index: 8092986 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.5650. Min Act: -0.1700
Data Index: 6620470 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.5650. Min Act: -0.1700
Data Index: 2701525 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.5650. Min Act: -0.1700
Data Index: 4437990 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.5650. Min Act: -0.1700
Data Index: 6075360 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.5025. Min Act: -0.1700
Data Index: 8092987 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.4713. Min Act: -0.1700
Data Index: 1082861 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.4713. Min Act: -0.1700
Data Index: 2200206 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.4713. Min Act: -0.1700
Data Index: 569990 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.4400. Min Act: -0.1700
Data Index: 5029023 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.4088. Min Act: -0.1700
Data Index: 2446889 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.4088. Min Act: -0.1700
Data Index: 3439990 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.4400. Min Act: -0.1700
Data Index: 1394492 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.4088. Min Act: -0.1700
Data Index: 1512042 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.4088. Min Act: -0.1700
Data Index: 6655990 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.3775. Min Act: -0.1700
Data Index: 5873851 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0338. Min Range: -6.0338
Max Act: 5.3775. Min Act: -0.1700
Data Index: 1769666 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19