Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2843 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8461. Min Range: -7.8461
Max Act: 7.8461. Min Act: -0.1700
Data Index: 3163927 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8461. Min Range: -7.8461
Max Act: 7.1899. Min Act: -0.1700
Data Index: 5949685 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8461. Min Range: -7.8461
Max Act: 7.0336. Min Act: -0.1700
Data Index: 3823442 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8461. Min Range: -7.8461
Max Act: 7.0024. Min Act: -0.1700
Data Index: 2058661 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.9399. Min Act: -0.1700
Data Index: 4095707 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.8774. Min Act: -0.1700
Data Index: 24172 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.8461. Min Act: -0.1700
Data Index: 3333397 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.8149. Min Act: -0.1700
Data Index: 5749286 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.7524. Min Act: -0.1700
Data Index: 2764968 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.7211. Min Act: -0.1700
Data Index: 4024923 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.6586. Min Act: -0.1700
Data Index: 2118712 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.5961. Min Act: -0.1700
Data Index: 2048196 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.5961. Min Act: -0.1700
Data Index: 4079354 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.5649. Min Act: -0.1700
Data Index: 7305453 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.5336. Min Act: -0.1700
Data Index: 8698669 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.5649. Min Act: -0.1700
Data Index: 749534 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.5336. Min Act: -0.1700
Data Index: 7820899 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.4711. Min Act: -0.1700
Data Index: 6073898 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.5024. Min Act: -0.1700
Data Index: 2048194 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8461. Min Range: -7.8461
Max Act: 6.4399. Min Act: -0.1700
Data Index: 7510996 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19