Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1325 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3917. Min Range: -9.3917
Max Act: 9.3917. Min Act: -0.1700
Data Index: 1716326 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3917. Min Range: -9.3917
Max Act: 9.2667. Min Act: -0.1700
Data Index: 4319379 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3917. Min Range: -9.3917
Max Act: 9.1417. Min Act: -0.1700
Data Index: 6939637 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3917. Min Range: -9.3917
Max Act: 9.0167. Min Act: -0.1700
Data Index: 8408651 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.9542. Min Act: -0.1700
Data Index: 5808701 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.8917. Min Act: -0.1700
Data Index: 6642953 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.8292. Min Act: -0.1700
Data Index: 6848736 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.8292. Min Act: -0.1700
Data Index: 8415291 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.8292. Min Act: -0.1700
Data Index: 1117494 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.8292. Min Act: -0.1700
Data Index: 6739100 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.8292. Min Act: -0.1700
Data Index: 2497453 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.8292. Min Act: -0.1700
Data Index: 7558720 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.7667. Min Act: -0.1700
Data Index: 5950458 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.7667. Min Act: -0.1700
Data Index: 302556 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.7042. Min Act: -0.1700
Data Index: 505428 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.7042. Min Act: -0.1700
Data Index: 6128466 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.7042. Min Act: -0.1700
Data Index: 1393604 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.7042. Min Act: -0.1700
Data Index: 1962910 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.7042. Min Act: -0.1700
Data Index: 1402142 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3917. Min Range: -9.3917
Max Act: 8.6417. Min Act: -0.1700
Data Index: 1080117 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19