Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3919 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3827. Min Act: -0.1700
Data Index: 5618454 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3827. Min Act: -0.1700
Data Index: 2819050 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3827. Min Act: -0.1700
Data Index: 2819061 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.4140. Min Act: -0.1700
Data Index: 6053430 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3827. Min Act: -0.1700
Data Index: 446150 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3515. Min Act: -0.1700
Data Index: 6718509 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3202. Min Act: -0.1700
Data Index: 5618453 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3202. Min Act: -0.1700
Data Index: 8491481 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.2890. Min Act: -0.1700
Data Index: 5665702 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3202. Min Act: -0.1700
Data Index: 5352642 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3202. Min Act: -0.1700
Data Index: 1516880 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3202. Min Act: -0.1700
Data Index: 3786720 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3202. Min Act: -0.1700
Data Index: 5440482 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.3202. Min Act: -0.1700
Data Index: 5774246 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.2890. Min Act: -0.1700
Data Index: 3863411 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.2577. Min Act: -0.1700
Data Index: 446161 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.2577. Min Act: -0.1700
Data Index: 3213901 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.2577. Min Act: -0.1700
Data Index: 446158 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.2577. Min Act: -0.1700
Data Index: 2391576 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4140. Min Range: -4.4140
Max Act: 4.2577. Min Act: -0.1700
Data Index: 3566225 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19