Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2762 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.9467. Min Act: -0.1700
Data Index: 2984896 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.9123. Min Act: -0.1700
Data Index: 2984897 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.7354. Min Act: -0.1700
Data Index: 2170622 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.7190. Min Act: -0.1700
Data Index: 5770353 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6945. Min Act: -0.1700
Data Index: 3448315 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6782. Min Act: -0.1700
Data Index: 8378497 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6701. Min Act: -0.1700
Data Index: 2372749 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6540. Min Act: -0.1700
Data Index: 8643860 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6460. Min Act: -0.1700
Data Index: 7694086 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6460. Min Act: -0.1700
Data Index: 3763311 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6380. Min Act: -0.1700
Data Index: 1002671 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6460. Min Act: -0.1700
Data Index: 1920741 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6460. Min Act: -0.1700
Data Index: 3625110 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6300. Min Act: -0.1699
Data Index: 1359992 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6300. Min Act: -0.1700
Data Index: 7353340 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6220. Min Act: -0.1700
Data Index: 2787135 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6220. Min Act: -0.1699
Data Index: 1477590 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6062. Min Act: -0.1635
Data Index: 7694098 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6141. Min Act: -0.1700
Data Index: 8220629 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9467. Min Range: -0.9467
Max Act: 0.6141. Min Act: -0.1700
Data Index: 2787126 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19