Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.6970. Min Act: -0.1700
Data Index: 4609246 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.6345. Min Act: -0.1700
Data Index: 1496012 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.5407. Min Act: -0.1700
Data Index: 8129841 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.5407. Min Act: -0.1700
Data Index: 5350141 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.5095. Min Act: -0.1700
Data Index: 1767829 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.4157. Min Act: -0.1700
Data Index: 2630342 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.4157. Min Act: -0.1700
Data Index: 6647690 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.3845. Min Act: -0.1700
Data Index: 7322731 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.3845. Min Act: -0.1700
Data Index: 6661312 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.3220. Min Act: -0.1700
Data Index: 3480734 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.3845. Min Act: -0.1700
Data Index: 5630428 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.3532. Min Act: -0.1700
Data Index: 1304166 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.3220. Min Act: -0.1700
Data Index: 3077131 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.2907. Min Act: -0.1700
Data Index: 1515199 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.2907. Min Act: -0.1700
Data Index: 7749158 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.2907. Min Act: -0.1700
Data Index: 7526119 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.2595. Min Act: -0.1700
Data Index: 8641656 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.2595. Min Act: -0.1700
Data Index: 390020 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.1970. Min Act: -0.1700
Data Index: 2576063 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6970. Min Range: -6.6970
Max Act: 6.1657. Min Act: -0.1700
Data Index: 1495469 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19