Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.6218. Min Act: -0.1700
Data Index: 4532961 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.5905. Min Act: -0.1700
Data Index: 3402843 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.5905. Min Act: -0.1700
Data Index: 538925 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.5905. Min Act: -0.1700
Data Index: 7830303 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.5905. Min Act: -0.1700
Data Index: 553478 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4968. Min Act: -0.1700
Data Index: 4752973 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4968. Min Act: -0.1700
Data Index: 7722180 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4655. Min Act: -0.1700
Data Index: 6292569 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4655. Min Act: -0.1700
Data Index: 6769350 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4655. Min Act: -0.1700
Data Index: 6875192 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4655. Min Act: -0.1700
Data Index: 3840001 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4655. Min Act: -0.1700
Data Index: 5099626 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4655. Min Act: -0.1700
Data Index: 8771705 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4343. Min Act: -0.1700
Data Index: 5949826 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4343. Min Act: -0.1700
Data Index: 8829049 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4030. Min Act: -0.1700
Data Index: 5067308 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4343. Min Act: -0.1700
Data Index: 8536012 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4343. Min Act: -0.1700
Data Index: 2107415 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4343. Min Act: -0.1700
Data Index: 4818418 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6218. Min Range: -5.6218
Max Act: 5.4655. Min Act: -0.1700
Data Index: 5982863 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19