Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6699. Min Range: -8.6699
Max Act: 8.6699. Min Act: -0.1700
Data Index: 123805 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6699. Min Range: -8.6699
Max Act: 8.3574. Min Act: -0.1700
Data Index: 1447052 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6699. Min Range: -8.6699
Max Act: 8.1699. Min Act: -0.1700
Data Index: 2202216 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6699. Min Range: -8.6699
Max Act: 8.1074. Min Act: -0.1700
Data Index: 558282 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6699. Min Range: -8.6699
Max Act: 8.0449. Min Act: -0.1700
Data Index: 7284361 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6699. Min Range: -8.6699
Max Act: 8.0449. Min Act: -0.1700
Data Index: 4316814 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6699. Min Range: -8.6699
Max Act: 8.0449. Min Act: -0.1700
Data Index: 80577 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6699. Min Range: -8.6699
Max Act: 8.0449. Min Act: -0.1700
Data Index: 8131258 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.9199. Min Act: -0.1700
Data Index: 5837037 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.8574. Min Act: -0.1700
Data Index: 2682259 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.8886. Min Act: -0.1700
Data Index: 3386970 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.8574. Min Act: -0.1700
Data Index: 3885860 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.8261. Min Act: -0.1700
Data Index: 899605 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.8261. Min Act: -0.1700
Data Index: 4053155 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.8261. Min Act: -0.1700
Data Index: 4812766 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.7949. Min Act: -0.1700
Data Index: 2929321 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.7949. Min Act: -0.1700
Data Index: 7982402 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.7324. Min Act: -0.1700
Data Index: 8063490 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.7636. Min Act: -0.1700
Data Index: 1266294 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6699. Min Range: -8.6699
Max Act: 7.7636. Min Act: -0.1700
Data Index: 6920341 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19