Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1149 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1430. Min Range: -4.1430
Max Act: 4.1430. Min Act: -0.1700
Data Index: 2107811 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1430. Min Range: -4.1430
Max Act: 4.0180. Min Act: -0.1700
Data Index: 6681016 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.9242. Min Act: -0.1700
Data Index: 4856205 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.9242. Min Act: -0.1700
Data Index: 7357373 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.9555. Min Act: -0.1700
Data Index: 3286600 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.9242. Min Act: -0.1700
Data Index: 7483804 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8930. Min Act: -0.1700
Data Index: 488498 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.9242. Min Act: -0.1700
Data Index: 2886065 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8930. Min Act: -0.1700
Data Index: 8346909 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8930. Min Act: -0.1700
Data Index: 3532606 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8930. Min Act: -0.1700
Data Index: 5025210 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8930. Min Act: -0.1700
Data Index: 3810424 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8617. Min Act: -0.1700
Data Index: 6005467 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8617. Min Act: -0.1700
Data Index: 860325 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8617. Min Act: -0.1700
Data Index: 8381630 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8617. Min Act: -0.1700
Data Index: 8494682 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8304. Min Act: -0.1700
Data Index: 4422982 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8617. Min Act: -0.1700
Data Index: 1187564 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.7992. Min Act: -0.1700
Data Index: 4390987 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1430. Min Range: -4.1430
Max Act: 3.8304. Min Act: -0.1700
Data Index: 4619570 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19