Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.5145. Min Act: -0.1700
Data Index: 3594146 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.3895. Min Act: -0.1700
Data Index: 1241644 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.3895. Min Act: -0.1700
Data Index: 7462220 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.3270. Min Act: -0.1700
Data Index: 2143272 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.2645. Min Act: -0.1700
Data Index: 7473614 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.2020. Min Act: -0.1700
Data Index: 8161425 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.0770. Min Act: -0.1700
Data Index: 2098239 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.1395. Min Act: -0.1700
Data Index: 3819092 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.0770. Min Act: -0.1700
Data Index: 3834211 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.0145. Min Act: -0.1700
Data Index: 7694275 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.0145. Min Act: -0.1700
Data Index: 5855485 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5145. Min Range: -10.5145
Max Act: 10.0145. Min Act: -0.1700
Data Index: 1808048 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5145. Min Range: -10.5145
Max Act: 9.9520. Min Act: -0.1700
Data Index: 1902564 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5145. Min Range: -10.5145
Max Act: 9.9520. Min Act: -0.1700
Data Index: 3023571 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5145. Min Range: -10.5145
Max Act: 9.8895. Min Act: -0.1700
Data Index: 345130 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5145. Min Range: -10.5145
Max Act: 9.8895. Min Act: -0.1700
Data Index: 2504594 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5145. Min Range: -10.5145
Max Act: 9.8895. Min Act: -0.1700
Data Index: 8185110 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5145. Min Range: -10.5145
Max Act: 9.8895. Min Act: -0.1700
Data Index: 3092565 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5145. Min Range: -10.5145
Max Act: 9.8895. Min Act: -0.1700
Data Index: 1195230 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5145. Min Range: -10.5145
Max Act: 9.8270. Min Act: -0.1700
Data Index: 4197549 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19