Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 78 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.3217. Min Act: -0.1700
Data Index: 3109235 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.1655. Min Act: -0.1700
Data Index: 5167835 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.1030. Min Act: -0.1700
Data Index: 3376972 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.9467. Min Act: -0.1700
Data Index: 3934896 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.9467. Min Act: -0.1700
Data Index: 4228438 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.8842. Min Act: -0.1700
Data Index: 7313974 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.8530. Min Act: -0.1700
Data Index: 6100116 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.8217. Min Act: -0.1700
Data Index: 5401334 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.7592. Min Act: -0.1700
Data Index: 1970675 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.7592. Min Act: -0.1700
Data Index: 628098 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.7592. Min Act: -0.1700
Data Index: 2278511 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.7905. Min Act: -0.1700
Data Index: 4430976 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.7905. Min Act: -0.1700
Data Index: 2078331 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.6967. Min Act: -0.1700
Data Index: 5407446 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.6967. Min Act: -0.1700
Data Index: 1169063 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.6967. Min Act: -0.1700
Data Index: 8720099 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.6967. Min Act: -0.1700
Data Index: 8446361 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.7280. Min Act: -0.1700
Data Index: 8106785 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.6967. Min Act: -0.1700
Data Index: 107653 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.6655. Min Act: -0.1700
Data Index: 3554157 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19