Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0493. Min Range: -7.0493
Max Act: 7.0493. Min Act: -0.1700
Data Index: 8191685 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0493. Min Range: -7.0493
Max Act: 7.0493. Min Act: -0.1700
Data Index: 7952851 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.9243. Min Act: -0.1700
Data Index: 4584580 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.8618. Min Act: -0.1700
Data Index: 2890837 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.8305. Min Act: -0.1700
Data Index: 701194 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.8618. Min Act: -0.1700
Data Index: 401590 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.8305. Min Act: -0.1700
Data Index: 6629690 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.8305. Min Act: -0.1700
Data Index: 1107645 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.7993. Min Act: -0.1700
Data Index: 2419563 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.7993. Min Act: -0.1700
Data Index: 2758900 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.7993. Min Act: -0.1700
Data Index: 3884239 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.7368. Min Act: -0.1700
Data Index: 3747136 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.6743. Min Act: -0.1700
Data Index: 2045417 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.6430. Min Act: -0.1700
Data Index: 1809962 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.6430. Min Act: -0.1700
Data Index: 4216109 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.6118. Min Act: -0.1700
Data Index: 3238888 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.6118. Min Act: -0.1700
Data Index: 6785462 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.6118. Min Act: -0.1700
Data Index: 7261510 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.5805. Min Act: -0.1700
Data Index: 5508978 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0493. Min Range: -7.0493
Max Act: 6.5493. Min Act: -0.1700
Data Index: 6172888 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19