Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.4618. Min Act: -0.1700
Data Index: 303842 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.3368. Min Act: -0.1700
Data Index: 4725194 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.3368. Min Act: -0.1700
Data Index: 2158535 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.3368. Min Act: -0.1700
Data Index: 8598427 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.3055. Min Act: -0.1700
Data Index: 1807907 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.2743. Min Act: -0.1700
Data Index: 7068075 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.2430. Min Act: -0.1700
Data Index: 6757690 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.2430. Min Act: -0.1700
Data Index: 3910078 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.2430. Min Act: -0.1700
Data Index: 5831159 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1805. Min Act: -0.1700
Data Index: 3149983 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1493. Min Act: -0.1700
Data Index: 685758 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1805. Min Act: -0.1700
Data Index: 7094962 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1805. Min Act: -0.1700
Data Index: 657019 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1805. Min Act: -0.1700
Data Index: 5189927 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1805. Min Act: -0.1700
Data Index: 244018 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1493. Min Act: -0.1700
Data Index: 7962890 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1493. Min Act: -0.1700
Data Index: 2738601 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1493. Min Act: -0.1700
Data Index: 902482 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1180. Min Act: -0.1700
Data Index: 1196599 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4618. Min Range: -5.4618
Max Act: 5.1493. Min Act: -0.1700
Data Index: 2784151 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19