Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 916 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1668. Min Range: -4.1668
Max Act: 4.1668. Min Act: -0.1700
Data Index: 7918257 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1668. Min Range: -4.1668
Max Act: 4.0730. Min Act: -0.1700
Data Index: 8144537 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1668. Min Range: -4.1668
Max Act: 4.0417. Min Act: -0.1700
Data Index: 4950030 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1668. Min Range: -4.1668
Max Act: 4.0417. Min Act: -0.1700
Data Index: 8094748 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1668. Min Range: -4.1668
Max Act: 4.0105. Min Act: -0.1700
Data Index: 5047211 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1668. Min Range: -4.1668
Max Act: 4.0105. Min Act: -0.1700
Data Index: 2214027 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.9792. Min Act: -0.1700
Data Index: 8094747 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.9792. Min Act: -0.1700
Data Index: 806443 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.9480. Min Act: -0.1700
Data Index: 671193 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.9011. Min Act: -0.1700
Data Index: 3958582 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.9011. Min Act: -0.1700
Data Index: 2055368 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.9011. Min Act: -0.1700
Data Index: 4950031 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.9167. Min Act: -0.1700
Data Index: 7997285 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.9011. Min Act: -0.1700
Data Index: 7105274 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.8854. Min Act: -0.1700
Data Index: 2244545 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.8854. Min Act: -0.1700
Data Index: 4709360 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.8698. Min Act: -0.1700
Data Index: 3368001 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.8698. Min Act: -0.1700
Data Index: 7206410 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.8698. Min Act: -0.1700
Data Index: 5731896 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1668. Min Range: -4.1668
Max Act: 3.8698. Min Act: -0.1700
Data Index: 7212261 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19