Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6036 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2365. Min Range: -7.2365
Max Act: 7.2365. Min Act: -0.1700
Data Index: 7022988 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2365. Min Range: -7.2365
Max Act: 7.1115. Min Act: -0.1700
Data Index: 581375 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.9865. Min Act: -0.1700
Data Index: 4671668 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2365. Min Range: -7.2365
Max Act: 7.0177. Min Act: -0.1700
Data Index: 4421614 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.7990. Min Act: -0.1700
Data Index: 1868178 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.8302. Min Act: -0.1700
Data Index: 298448 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.7990. Min Act: -0.1700
Data Index: 915201 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.7677. Min Act: -0.1700
Data Index: 8723263 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.7365. Min Act: -0.1700
Data Index: 2556227 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.7052. Min Act: -0.1700
Data Index: 4671670 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.7052. Min Act: -0.1700
Data Index: 6827722 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.6427. Min Act: -0.1700
Data Index: 915200 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.7052. Min Act: -0.1700
Data Index: 581370 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.7052. Min Act: -0.1700
Data Index: 681084 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.6427. Min Act: -0.1700
Data Index: 5919876 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.6427. Min Act: -0.1700
Data Index: 896669 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.6115. Min Act: -0.1700
Data Index: 915190 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.6740. Min Act: -0.1700
Data Index: 496118 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.6427. Min Act: -0.1700
Data Index: 4428173 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2365. Min Range: -7.2365
Max Act: 6.6427. Min Act: -0.1700
Data Index: 681092 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19