Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 585 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3731. Min Range: -6.3731
Max Act: 6.3731. Min Act: -0.1700
Data Index: 3602541 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3731. Min Range: -6.3731
Max Act: 6.3731. Min Act: -0.1700
Data Index: 2266981 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3731. Min Range: -6.3731
Max Act: 6.2168. Min Act: -0.1700
Data Index: 1671820 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3731. Min Range: -6.3731
Max Act: 6.0918. Min Act: -0.1700
Data Index: 5567961 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3731. Min Range: -6.3731
Max Act: 6.0918. Min Act: -0.1700
Data Index: 1936172 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3731. Min Range: -6.3731
Max Act: 6.0606. Min Act: -0.1700
Data Index: 4431411 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3731. Min Range: -6.3731
Max Act: 6.0918. Min Act: -0.1700
Data Index: 1930809 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.9668. Min Act: -0.1700
Data Index: 519224 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.9356. Min Act: -0.1700
Data Index: 4421523 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.9043. Min Act: -0.1700
Data Index: 3536880 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.9356. Min Act: -0.1700
Data Index: 8563520 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.8731. Min Act: -0.1700
Data Index: 2631921 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.8106. Min Act: -0.1700
Data Index: 4694861 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.8418. Min Act: -0.1700
Data Index: 4952240 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.8418. Min Act: -0.1700
Data Index: 303244 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.8106. Min Act: -0.1700
Data Index: 5135752 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.8106. Min Act: -0.1700
Data Index: 4004492 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.8106. Min Act: -0.1700
Data Index: 1472090 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.7793. Min Act: -0.1700
Data Index: 4166588 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3731. Min Range: -6.3731
Max Act: 5.8106. Min Act: -0.1700
Data Index: 1927971 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19