Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3917 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.4590. Min Act: -0.1700
Data Index: 1760978 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.3340. Min Act: -0.1700
Data Index: 1736149 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.3340. Min Act: -0.1700
Data Index: 7049487 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.3027. Min Act: -0.1700
Data Index: 3075887 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.3027. Min Act: -0.1700
Data Index: 7534230 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.3027. Min Act: -0.1700
Data Index: 2697328 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.3027. Min Act: -0.1700
Data Index: 7611946 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.2402. Min Act: -0.1700
Data Index: 2384657 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.2402. Min Act: -0.1700
Data Index: 3593744 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.2089. Min Act: -0.1700
Data Index: 8544811 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.2089. Min Act: -0.1700
Data Index: 2288280 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.2089. Min Act: -0.1700
Data Index: 8610210 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.2089. Min Act: -0.1700
Data Index: 4894234 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.1777. Min Act: -0.1700
Data Index: 3099571 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.1777. Min Act: -0.1700
Data Index: 4175344 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.1777. Min Act: -0.1700
Data Index: 7857595 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.1777. Min Act: -0.1700
Data Index: 8694814 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.1777. Min Act: -0.1700
Data Index: 2024335 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.1152. Min Act: -0.1700
Data Index: 5480538 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4590. Min Range: -4.4590
Max Act: 4.1152. Min Act: -0.1700
Data Index: 2296287 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19