Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2776 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8928. Min Range: -8.8928
Max Act: 8.8928. Min Act: -0.1700
Data Index: 725659 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8928. Min Range: -8.8928
Max Act: 8.3303. Min Act: -0.1700
Data Index: 1973932 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8928. Min Range: -8.8928
Max Act: 8.2053. Min Act: -0.1700
Data Index: 6015228 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8928. Min Range: -8.8928
Max Act: 8.2678. Min Act: -0.1700
Data Index: 6197480 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8928. Min Range: -8.8928
Max Act: 8.1428. Min Act: -0.1700
Data Index: 280562 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8928. Min Range: -8.8928
Max Act: 8.1428. Min Act: -0.1700
Data Index: 6274252 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8928. Min Range: -8.8928
Max Act: 8.0803. Min Act: -0.1700
Data Index: 4368052 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8928. Min Range: -8.8928
Max Act: 8.0491. Min Act: -0.1700
Data Index: 6216832 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8928. Min Range: -8.8928
Max Act: 8.0491. Min Act: -0.1700
Data Index: 5742358 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.9241. Min Act: -0.1700
Data Index: 3574586 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.8616. Min Act: -0.1700
Data Index: 1894704 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.8928. Min Act: -0.1700
Data Index: 2214786 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.8928. Min Act: -0.1700
Data Index: 7965081 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.8303. Min Act: -0.1700
Data Index: 8156838 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.8303. Min Act: -0.1700
Data Index: 8640618 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.7991. Min Act: -0.1700
Data Index: 2614961 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.7366. Min Act: -0.1700
Data Index: 1900982 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.7366. Min Act: -0.1700
Data Index: 6431893 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.7678. Min Act: -0.1700
Data Index: 8519544 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8928. Min Range: -8.8928
Max Act: 7.7678. Min Act: -0.1700
Data Index: 4397075 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19