Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 83 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.5018. Min Act: -0.1700
Data Index: 1382087 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.4393. Min Act: -0.1700
Data Index: 3991828 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.4393. Min Act: -0.1700
Data Index: 976778 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.3456. Min Act: -0.1700
Data Index: 483291 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.3456. Min Act: -0.1700
Data Index: 4937228 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.3456. Min Act: -0.1700
Data Index: 3198931 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.3456. Min Act: -0.1700
Data Index: 4205405 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.2518. Min Act: -0.1700
Data Index: 4091456 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.2518. Min Act: -0.1700
Data Index: 4091452 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.2206. Min Act: -0.1700
Data Index: 3733384 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.1893. Min Act: -0.1700
Data Index: 5002184 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.1580. Min Act: -0.1700
Data Index: 782552 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.1268. Min Act: -0.1700
Data Index: 8637033 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.0955. Min Act: -0.1700
Data Index: 4075575 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.0955. Min Act: -0.1700
Data Index: 6338334 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.1268. Min Act: -0.1700
Data Index: 6000003 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.0955. Min Act: -0.1700
Data Index: 5712164 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.0955. Min Act: -0.1700
Data Index: 2765430 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.0643. Min Act: -0.1700
Data Index: 4091454 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5018. Min Range: -4.5018
Max Act: 4.0643. Min Act: -0.1700
Data Index: 4504360 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19