Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0275. Min Range: -6.0275
Max Act: 6.0275. Min Act: -0.1700
Data Index: 1137331 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.8713. Min Act: -0.1700
Data Index: 1015744 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.8088. Min Act: -0.1700
Data Index: 6784197 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.7775. Min Act: -0.1700
Data Index: 2757382 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.8088. Min Act: -0.1700
Data Index: 3029263 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.7775. Min Act: -0.1700
Data Index: 4674894 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.7775. Min Act: -0.1700
Data Index: 7138928 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.7463. Min Act: -0.1700
Data Index: 6863030 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.7775. Min Act: -0.1700
Data Index: 5480472 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.7150. Min Act: -0.1700
Data Index: 2371629 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.6838. Min Act: -0.1700
Data Index: 7822022 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.6525. Min Act: -0.1700
Data Index: 410297 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.6213. Min Act: -0.1700
Data Index: 1631160 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.6525. Min Act: -0.1700
Data Index: 3274364 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.6525. Min Act: -0.1700
Data Index: 3435209 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.6213. Min Act: -0.1700
Data Index: 473299 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.5900. Min Act: -0.1700
Data Index: 3298678 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.5900. Min Act: -0.1700
Data Index: 6057038 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.5900. Min Act: -0.1700
Data Index: 47222 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0275. Min Range: -6.0275
Max Act: 5.6213. Min Act: -0.1700
Data Index: 400420 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19