Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5069 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.7213. Min Act: -0.1700
Data Index: 2780541 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.7213. Min Act: -0.1700
Data Index: 8706041 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.5651. Min Act: -0.1700
Data Index: 5777964 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.5651. Min Act: -0.1700
Data Index: 393272 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.4713. Min Act: -0.1700
Data Index: 5988389 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.4713. Min Act: -0.1700
Data Index: 4437443 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.4401. Min Act: -0.1700
Data Index: 4956406 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.4401. Min Act: -0.1700
Data Index: 1421568 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.4088. Min Act: -0.1700
Data Index: 6441843 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.4088. Min Act: -0.1700
Data Index: 7040367 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.4088. Min Act: -0.1700
Data Index: 6227421 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.3776. Min Act: -0.1700
Data Index: 771712 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.3776. Min Act: -0.1700
Data Index: 2261485 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.4088. Min Act: -0.1700
Data Index: 1836566 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.3776. Min Act: -0.1700
Data Index: 8612245 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.3776. Min Act: -0.1700
Data Index: 2780542 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.3776. Min Act: -0.1700
Data Index: 7336832 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.3463. Min Act: -0.1700
Data Index: 1730944 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.3463. Min Act: -0.1700
Data Index: 2215139 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7213. Min Range: -5.7213
Max Act: 5.3463. Min Act: -0.1700
Data Index: 6614481 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19