Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4273 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1772. Min Range: -7.1772
Max Act: 7.1772. Min Act: -0.1700
Data Index: 4073290 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.8022. Min Act: -0.1700
Data Index: 3292226 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.7084. Min Act: -0.1700
Data Index: 1371885 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.6147. Min Act: -0.1700
Data Index: 6662426 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.6147. Min Act: -0.1700
Data Index: 158170 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.5834. Min Act: -0.1700
Data Index: 1674751 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.5522. Min Act: -0.1700
Data Index: 8337389 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.5209. Min Act: -0.1700
Data Index: 56119 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.4897. Min Act: -0.1700
Data Index: 7700078 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.5209. Min Act: -0.1700
Data Index: 6623618 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.4897. Min Act: -0.1700
Data Index: 8583610 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.4897. Min Act: -0.1700
Data Index: 6852531 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.4272. Min Act: -0.1700
Data Index: 7920913 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.4897. Min Act: -0.1700
Data Index: 1265623 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.4272. Min Act: -0.1700
Data Index: 5508905 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.4272. Min Act: -0.1700
Data Index: 5972853 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.4272. Min Act: -0.1700
Data Index: 7196784 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.3959. Min Act: -0.1700
Data Index: 5466107 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.3959. Min Act: -0.1700
Data Index: 1218740 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1772. Min Range: -7.1772
Max Act: 6.3959. Min Act: -0.1700
Data Index: 7731724 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19