Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3276. Min Range: -6.3276
Max Act: 6.3276. Min Act: -0.1700
Data Index: 7168233 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3276. Min Range: -6.3276
Max Act: 6.1401. Min Act: -0.1700
Data Index: 5865288 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3276. Min Range: -6.3276
Max Act: 6.0151. Min Act: -0.1700
Data Index: 1391232 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.9526. Min Act: -0.1700
Data Index: 319488 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.9526. Min Act: -0.1700
Data Index: 7483088 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.9526. Min Act: -0.1700
Data Index: 2925710 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.9839. Min Act: -0.1700
Data Index: 8435751 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.9526. Min Act: -0.1700
Data Index: 5791048 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.8901. Min Act: -0.1700
Data Index: 3788929 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.8901. Min Act: -0.1700
Data Index: 7142852 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.8276. Min Act: -0.1700
Data Index: 90879 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.8276. Min Act: -0.1700
Data Index: 2391042 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.7964. Min Act: -0.1700
Data Index: 335860 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.7651. Min Act: -0.1700
Data Index: 1413464 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.7651. Min Act: -0.1700
Data Index: 7042397 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.7651. Min Act: -0.1700
Data Index: 1692276 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.7339. Min Act: -0.1700
Data Index: 3311912 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.7339. Min Act: -0.1700
Data Index: 39131 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.7651. Min Act: -0.1700
Data Index: 1568939 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3276. Min Range: -6.3276
Max Act: 5.7339. Min Act: -0.1700
Data Index: 217696 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19