Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5581 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.8333. Min Act: -0.1700
Data Index: 8467162 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.5521. Min Act: -0.1700
Data Index: 7499050 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.4583. Min Act: -0.1700
Data Index: 5834487 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.4271. Min Act: -0.1700
Data Index: 3716254 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.3333. Min Act: -0.1700
Data Index: 6031889 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.3021. Min Act: -0.1700
Data Index: 6436865 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.3021. Min Act: -0.1700
Data Index: 7554742 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.3333. Min Act: -0.1700
Data Index: 1886118 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.2708. Min Act: -0.1700
Data Index: 7907429 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.2396. Min Act: -0.1700
Data Index: 7770074 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.2083. Min Act: -0.1700
Data Index: 3717905 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.2083. Min Act: -0.1700
Data Index: 7030193 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.2083. Min Act: -0.1700
Data Index: 7582284 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.1771. Min Act: -0.1700
Data Index: 8095373 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.1771. Min Act: -0.1700
Data Index: 4059020 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.1771. Min Act: -0.1700
Data Index: 53327 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.1458. Min Act: -0.1700
Data Index: 4094848 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.1458. Min Act: -0.1700
Data Index: 7616323 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.1458. Min Act: -0.1700
Data Index: 2080224 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.1458. Min Act: -0.1700
Data Index: 7276598 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19