Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1624 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.1564. Min Range: -9.1564
Max Act: 9.1564. Min Act: -0.1700
Data Index: 6261867 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.7814. Min Act: -0.1700
Data Index: 5218365 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.5939. Min Act: -0.1700
Data Index: 3359730 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.5314. Min Act: -0.1700
Data Index: 1757596 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.5314. Min Act: -0.1700
Data Index: 3771920 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.5314. Min Act: -0.1700
Data Index: 747056 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.4689. Min Act: -0.1700
Data Index: 1388242 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.4689. Min Act: -0.1700
Data Index: 276885 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.5314. Min Act: -0.1700
Data Index: 1868290 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.3439. Min Act: -0.1700
Data Index: 5807702 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.3439. Min Act: -0.1700
Data Index: 1123911 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.3439. Min Act: -0.1700
Data Index: 1314859 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.3439. Min Act: -0.1700
Data Index: 1694753 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.3439. Min Act: -0.1700
Data Index: 4644932 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.2814. Min Act: -0.1700
Data Index: 7195167 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.2814. Min Act: -0.1700
Data Index: 7260877 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.2814. Min Act: -0.1700
Data Index: 130107 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.2814. Min Act: -0.1700
Data Index: 7783796 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.2501. Min Act: -0.1700
Data Index: 5801260 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1564. Min Range: -9.1564
Max Act: 8.2814. Min Act: -0.1700
Data Index: 3420777 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19