Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.5654. Min Act: -0.1700
Data Index: 583217 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.5029. Min Act: -0.1700
Data Index: 1947414 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.5029. Min Act: -0.1700
Data Index: 680451 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.4717. Min Act: -0.1700
Data Index: 1000128 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.3467. Min Act: -0.1700
Data Index: 2674106 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.3467. Min Act: -0.1700
Data Index: 7241032 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.3467. Min Act: -0.1700
Data Index: 4557825 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.3467. Min Act: -0.1700
Data Index: 1670285 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2842. Min Act: -0.1700
Data Index: 8410075 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2842. Min Act: -0.1700
Data Index: 7672287 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2529. Min Act: -0.0662
Data Index: 1119137 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2529. Min Act: -0.1700
Data Index: 8625251 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2529. Min Act: -0.1699
Data Index: 7749609 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2529. Min Act: -0.1700
Data Index: 7440135 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2217. Min Act: -0.1700
Data Index: 473584 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2217. Min Act: -0.1700
Data Index: 4116023 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2842. Min Act: -0.1700
Data Index: 3124636 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2217. Min Act: -0.1700
Data Index: 1210694 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2217. Min Act: -0.1700
Data Index: 8015532 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5654. Min Range: -5.5654
Max Act: 5.2217. Min Act: -0.1700
Data Index: 3928751 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19