Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2659 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.9647. Min Act: -0.1700
Data Index: 3330434 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.9022. Min Act: -0.1700
Data Index: 3566580 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.8085. Min Act: -0.1700
Data Index: 152299 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.8085. Min Act: -0.1700
Data Index: 8382523 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.7460. Min Act: -0.1700
Data Index: 5816784 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.7772. Min Act: -0.1700
Data Index: 5155459 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.7147. Min Act: -0.1700
Data Index: 5940141 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.6210. Min Act: -0.1700
Data Index: 6358515 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.6210. Min Act: -0.1700
Data Index: 967160 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.5272. Min Act: -0.1700
Data Index: 876382 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.5585. Min Act: -0.1700
Data Index: 5940139 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.4960. Min Act: -0.1700
Data Index: 7305479 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.4647. Min Act: -0.1700
Data Index: 3089094 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.4647. Min Act: -0.1700
Data Index: 4477077 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.4647. Min Act: -0.1700
Data Index: 5940140 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.4335. Min Act: -0.1700
Data Index: 7625129 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.4335. Min Act: -0.1700
Data Index: 1773884 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.4647. Min Act: -0.1700
Data Index: 1456936 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.4022. Min Act: -0.1700
Data Index: 24683 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9647. Min Range: -5.9647
Max Act: 5.3710. Min Act: -0.1700
Data Index: 387351 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19