Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1782 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4157. Min Range: -8.4157
Max Act: 8.4157. Min Act: -0.1700
Data Index: 1478390 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4157. Min Range: -8.4157
Max Act: 8.0407. Min Act: -0.1700
Data Index: 7570056 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.7282. Min Act: -0.1700
Data Index: 398883 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.7282. Min Act: -0.1700
Data Index: 6778082 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.7282. Min Act: -0.1700
Data Index: 7494161 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.6657. Min Act: -0.1700
Data Index: 4217798 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.6032. Min Act: -0.1700
Data Index: 5709454 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.6032. Min Act: -0.1700
Data Index: 1335696 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.6657. Min Act: -0.1700
Data Index: 6739885 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.6032. Min Act: -0.1700
Data Index: 2155472 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.6032. Min Act: -0.1700
Data Index: 1334362 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.5407. Min Act: -0.1700
Data Index: 2679407 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.4782. Min Act: -0.1700
Data Index: 5793042 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.4470. Min Act: -0.1700
Data Index: 3896375 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.4470. Min Act: -0.1700
Data Index: 2724619 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.4157. Min Act: -0.1700
Data Index: 6207238 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.4157. Min Act: -0.1700
Data Index: 7820240 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.3845. Min Act: -0.1700
Data Index: 3599909 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.4157. Min Act: -0.1700
Data Index: 5905813 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4157. Min Range: -8.4157
Max Act: 7.3532. Min Act: -0.1700
Data Index: 2284392 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19