Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5952 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.5342. Min Act: -0.1700
Data Index: 3200780 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.4404. Min Act: -0.1700
Data Index: 4810924 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.4404. Min Act: -0.1700
Data Index: 1734142 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.3779. Min Act: -0.1700
Data Index: 5373173 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.3779. Min Act: -0.1700
Data Index: 8143851 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.3779. Min Act: -0.1700
Data Index: 670514 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.3779. Min Act: -0.1700
Data Index: 5185454 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.3467. Min Act: -0.1700
Data Index: 1179220 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.3154. Min Act: -0.1700
Data Index: 670512 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.3154. Min Act: -0.1700
Data Index: 2949781 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.2842. Min Act: -0.1700
Data Index: 5977088 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.2842. Min Act: -0.1700
Data Index: 670517 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.2842. Min Act: -0.1700
Data Index: 2236996 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.2842. Min Act: -0.1700
Data Index: 7428700 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.2842. Min Act: -0.1700
Data Index: 2174385 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.2529. Min Act: -0.1700
Data Index: 8549479 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.2529. Min Act: -0.1700
Data Index: 670515 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.2529. Min Act: -0.1700
Data Index: 670518 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.2217. Min Act: -0.1700
Data Index: 3000711 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5342. Min Range: -5.5342
Max Act: 5.2217. Min Act: -0.1700
Data Index: 5185453 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19