Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6247 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3326. Min Range: -9.3326
Max Act: 9.3326. Min Act: -0.1700
Data Index: 4074304 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.6451. Min Act: -0.1700
Data Index: 6111449 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.6451. Min Act: -0.1700
Data Index: 8055455 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.5826. Min Act: -0.1700
Data Index: 4420255 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.5826. Min Act: -0.1700
Data Index: 8456036 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.4576. Min Act: -0.1700
Data Index: 561093 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.5201. Min Act: -0.1700
Data Index: 2963108 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.3951. Min Act: -0.1700
Data Index: 6621399 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.3951. Min Act: -0.1700
Data Index: 8695636 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.3326. Min Act: -0.1700
Data Index: 3054384 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.3326. Min Act: -0.1700
Data Index: 8742190 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.3326. Min Act: -0.1700
Data Index: 7609909 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.3326. Min Act: -0.1700
Data Index: 7199985 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.2076. Min Act: -0.1700
Data Index: 8242129 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.2701. Min Act: -0.1700
Data Index: 3039112 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.2076. Min Act: -0.1700
Data Index: 4752538 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.2076. Min Act: -0.1700
Data Index: 4356809 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.2076. Min Act: -0.1700
Data Index: 561089 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.1451. Min Act: -0.1700
Data Index: 5030022 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3326. Min Range: -9.3326
Max Act: 8.1451. Min Act: -0.1699
Data Index: 3678180 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19