Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4817 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3802. Min Range: -6.3802
Max Act: 6.3802. Min Act: -0.1700
Data Index: 7489631 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3802. Min Range: -6.3802
Max Act: 6.0364. Min Act: -0.1700
Data Index: 2537544 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3802. Min Range: -6.3802
Max Act: 6.0364. Min Act: -0.1700
Data Index: 7936406 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3802. Min Range: -6.3802
Max Act: 6.0052. Min Act: -0.1700
Data Index: 4389189 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.9427. Min Act: -0.1700
Data Index: 930525 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.8177. Min Act: -0.1700
Data Index: 3175050 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7864. Min Act: -0.1700
Data Index: 766858 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7552. Min Act: -0.1700
Data Index: 1741123 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7552. Min Act: -0.1700
Data Index: 8324339 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7552. Min Act: -0.1700
Data Index: 5288293 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7552. Min Act: -0.1700
Data Index: 5907312 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7552. Min Act: -0.1700
Data Index: 5546259 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7552. Min Act: -0.1700
Data Index: 8376242 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7239. Min Act: -0.1700
Data Index: 26679 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7239. Min Act: -0.1700
Data Index: 2667622 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7552. Min Act: -0.1700
Data Index: 8746271 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7239. Min Act: -0.1700
Data Index: 8433000 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.6927. Min Act: -0.1700
Data Index: 5433762 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.7239. Min Act: -0.1700
Data Index: 2403179 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3802. Min Range: -6.3802
Max Act: 5.6927. Min Act: -0.1700
Data Index: 7882516 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19