Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.5521. Min Act: -0.1700
Data Index: 2055396 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.5208. Min Act: -0.1700
Data Index: 4498206 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.5208. Min Act: -0.1700
Data Index: 5781253 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.4896. Min Act: -0.1700
Data Index: 7585925 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.4896. Min Act: -0.1700
Data Index: 3519332 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.4896. Min Act: -0.1700
Data Index: 4233503 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.4271. Min Act: -0.1700
Data Index: 3284218 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.3958. Min Act: -0.1700
Data Index: 8539831 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.3958. Min Act: -0.1700
Data Index: 8826396 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.3333. Min Act: -0.1700
Data Index: 5114029 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.3333. Min Act: -0.1700
Data Index: 7558546 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.3021. Min Act: -0.1700
Data Index: 2847435 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.3021. Min Act: -0.1700
Data Index: 1529010 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.3021. Min Act: -0.1700
Data Index: 3989838 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.3021. Min Act: -0.1700
Data Index: 173493 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.3333. Min Act: -0.1700
Data Index: 352415 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.2708. Min Act: -0.1700
Data Index: 8297397 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.2708. Min Act: -0.1700
Data Index: 1152919 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.2708. Min Act: -0.1700
Data Index: 6605274 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5521. Min Range: -5.5521
Max Act: 5.2396. Min Act: -0.1700
Data Index: 1576572 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19