Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.6901. Min Act: -0.1700
Data Index: 5991000 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5651. Min Act: -0.1700
Data Index: 2749858 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5651. Min Act: -0.1700
Data Index: 5668176 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5026. Min Act: -0.1700
Data Index: 6207829 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5026. Min Act: -0.1700
Data Index: 5486294 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5026. Min Act: -0.1700
Data Index: 6928138 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5026. Min Act: -0.1700
Data Index: 3869567 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5026. Min Act: -0.1700
Data Index: 4126487 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5026. Min Act: -0.1700
Data Index: 2606418 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.4713. Min Act: -0.1700
Data Index: 6200959 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.4713. Min Act: -0.1700
Data Index: 8464186 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.4713. Min Act: -0.1700
Data Index: 1918572 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.4401. Min Act: -0.1700
Data Index: 5885956 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.4713. Min Act: -0.1700
Data Index: 254277 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.4713. Min Act: -0.1700
Data Index: 6965515 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.4713. Min Act: -0.1700
Data Index: 6885853 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5026. Min Act: -0.1700
Data Index: 6270960 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5026. Min Act: -0.1700
Data Index: 4991795 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.4713. Min Act: -0.1700
Data Index: 4596606 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6901. Min Range: -4.6901
Max Act: 4.5026. Min Act: -0.1700
Data Index: 2432576 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19