Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4102 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.1080. Min Act: -0.1700
Data Index: 8643679 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.1080. Min Act: -0.1700
Data Index: 6905940 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0767. Min Act: -0.1700
Data Index: 2098717 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0767. Min Act: -0.1700
Data Index: 6101038 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0767. Min Act: -0.1700
Data Index: 3149196 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0455. Min Act: -0.1700
Data Index: 5397396 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0455. Min Act: -0.1700
Data Index: 4859707 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0142. Min Act: -0.1700
Data Index: 527366 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0455. Min Act: -0.1700
Data Index: 8469453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0455. Min Act: -0.1700
Data Index: 1666978 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0455. Min Act: -0.1700
Data Index: 2292961 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0455. Min Act: -0.1700
Data Index: 5605796 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0455. Min Act: -0.1700
Data Index: 668367 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0142. Min Act: -0.1700
Data Index: 4103257 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0142. Min Act: -0.1700
Data Index: 1948373 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0142. Min Act: -0.1700
Data Index: 1386209 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0142. Min Act: -0.1700
Data Index: 4182117 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0142. Min Act: -0.1700
Data Index: 2001995 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0142. Min Act: -0.1700
Data Index: 350708 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1080. Min Range: -4.1080
Max Act: 4.0142. Min Act: -0.1700
Data Index: 4523085 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19