Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4471 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3224. Min Range: -7.3224
Max Act: 7.3224. Min Act: -0.1700
Data Index: 2382825 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.5724. Min Act: -0.1700
Data Index: 8572376 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.5099. Min Act: -0.1700
Data Index: 8320890 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.4787. Min Act: -0.1700
Data Index: 8620765 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.4474. Min Act: -0.1700
Data Index: 1951002 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.4162. Min Act: -0.1700
Data Index: 5100486 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.2599. Min Act: -0.1700
Data Index: 5995292 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.2287. Min Act: -0.1700
Data Index: 7919088 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.1662. Min Act: -0.1700
Data Index: 1905748 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.1974. Min Act: -0.1700
Data Index: 4369853 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.1349. Min Act: -0.1700
Data Index: 3462761 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.1349. Min Act: -0.1700
Data Index: 939304 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.1349. Min Act: -0.1700
Data Index: 6595255 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.1349. Min Act: -0.1700
Data Index: 6982803 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.1037. Min Act: -0.1700
Data Index: 8300579 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.1349. Min Act: -0.1700
Data Index: 5563857 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.1037. Min Act: -0.1700
Data Index: 90485 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.0724. Min Act: -0.1700
Data Index: 5647516 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.1037. Min Act: -0.1700
Data Index: 7087457 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3224. Min Range: -7.3224
Max Act: 6.0724. Min Act: -0.1700
Data Index: 886112 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19