Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4503 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3630. Min Range: -5.3630
Max Act: 5.3630. Min Act: -0.1700
Data Index: 861177 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3630. Min Range: -5.3630
Max Act: 5.0505. Min Act: -0.1700
Data Index: 8766835 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3630. Min Range: -5.3630
Max Act: 5.0505. Min Act: -0.1700
Data Index: 5607805 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.9255. Min Act: -0.1700
Data Index: 4650675 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.8943. Min Act: -0.1700
Data Index: 279624 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.8630. Min Act: -0.1700
Data Index: 2101553 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.8318. Min Act: -0.1700
Data Index: 392302 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.8005. Min Act: -0.1700
Data Index: 1446231 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.8005. Min Act: -0.1700
Data Index: 4600239 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.7693. Min Act: -0.1700
Data Index: 1312727 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.8005. Min Act: -0.1700
Data Index: 470820 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.8005. Min Act: -0.1700
Data Index: 6820193 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.8005. Min Act: -0.1700
Data Index: 6866992 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.7380. Min Act: -0.1700
Data Index: 2615518 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.7068. Min Act: -0.1700
Data Index: 723082 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.7068. Min Act: -0.1700
Data Index: 556300 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.6755. Min Act: -0.1700
Data Index: 1741040 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.6755. Min Act: -0.1700
Data Index: 1757770 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.6443. Min Act: -0.1700
Data Index: 497667 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3630. Min Range: -5.3630
Max Act: 4.6443. Min Act: -0.1700
Data Index: 2946366 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19