Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1403 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.5630. Min Act: -0.1700
Data Index: 5004822 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.5317. Min Act: -0.1700
Data Index: 5734774 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.4067. Min Act: -0.1700
Data Index: 8344783 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.2817. Min Act: -0.1700
Data Index: 7038944 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.2817. Min Act: -0.1700
Data Index: 3704998 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.2817. Min Act: -0.1700
Data Index: 3744816 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.2505. Min Act: -0.1700
Data Index: 538153 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1880. Min Act: -0.1700
Data Index: 6328244 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1880. Min Act: -0.1700
Data Index: 1204822 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1567. Min Act: -0.1700
Data Index: 634720 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1880. Min Act: -0.1700
Data Index: 5304232 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1255. Min Act: -0.1700
Data Index: 142405 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1567. Min Act: -0.1700
Data Index: 7249442 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1567. Min Act: -0.1700
Data Index: 4252984 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1567. Min Act: -0.1700
Data Index: 8515906 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1567. Min Act: -0.1700
Data Index: 6853348 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1567. Min Act: -0.1700
Data Index: 2092148 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1255. Min Act: -0.1700
Data Index: 2669604 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.1567. Min Act: -0.1700
Data Index: 3437421 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5630. Min Range: -5.5630
Max Act: 5.0630. Min Act: -0.1700
Data Index: 907137 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19