Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1692 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.4148. Min Act: -0.1700
Data Index: 900882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3207. Min Act: -0.1700
Data Index: 4214232 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2579. Min Act: -0.1700
Data Index: 7242219 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2265. Min Act: -0.1700
Data Index: 267347 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2265. Min Act: -0.1700
Data Index: 763959 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1950. Min Act: -0.1700
Data Index: 8379573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1950. Min Act: -0.1700
Data Index: 1198319 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1950. Min Act: -0.1700
Data Index: 1204566 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1950. Min Act: -0.1700
Data Index: 3132073 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1950. Min Act: -0.1700
Data Index: 2425969 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1950. Min Act: -0.1700
Data Index: 4971535 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1950. Min Act: -0.1700
Data Index: 6286667 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1950. Min Act: -0.1700
Data Index: 6208271 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1636. Min Act: -0.1700
Data Index: 7183610 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1636. Min Act: -0.1700
Data Index: 3543765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1636. Min Act: -0.1700
Data Index: 6095936 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1636. Min Act: -0.1700
Data Index: 1910183 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1636. Min Act: -0.1700
Data Index: 359434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1636. Min Act: -0.1700
Data Index: 64224 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.1636. Min Act: -0.1700
Data Index: 3090391 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19