Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.2217. Min Act: -0.1700
Data Index: 7510976 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.1592. Min Act: -0.1700
Data Index: 3106478 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0654. Min Act: -0.1700
Data Index: 1152591 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0342. Min Act: -0.1700
Data Index: 7445912 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0342. Min Act: -0.1700
Data Index: 1502216 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0342. Min Act: -0.1700
Data Index: 4550778 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0342. Min Act: -0.1700
Data Index: 4591353 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0342. Min Act: -0.1700
Data Index: 8767152 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0342. Min Act: -0.1700
Data Index: 3227617 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0342. Min Act: -0.1700
Data Index: 7141751 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0342. Min Act: -0.1700
Data Index: 4886959 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0342. Min Act: -0.1700
Data Index: 7165179 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0029. Min Act: -0.1700
Data Index: 3287838 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2217. Min Range: -4.2217
Max Act: 3.9717. Min Act: -0.1700
Data Index: 2989994 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2217. Min Range: -4.2217
Max Act: 3.9717. Min Act: -0.1700
Data Index: 778865 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2217. Min Range: -4.2217
Max Act: 3.9404. Min Act: -0.1700
Data Index: 7154724 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2217. Min Range: -4.2217
Max Act: 4.0029. Min Act: -0.1700
Data Index: 8440613 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2217. Min Range: -4.2217
Max Act: 3.9717. Min Act: -0.1700
Data Index: 852360 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2217. Min Range: -4.2217
Max Act: 3.9404. Min Act: -0.1700
Data Index: 3639587 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2217. Min Range: -4.2217
Max Act: 3.9717. Min Act: -0.1700
Data Index: 8401213 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19