Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 494 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.4880. Min Act: -0.1700
Data Index: 5534025 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.3318. Min Act: -0.1700
Data Index: 5804645 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.2693. Min Act: -0.1700
Data Index: 6042421 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.2380. Min Act: -0.1700
Data Index: 7288285 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.2380. Min Act: -0.1700
Data Index: 8516807 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.2380. Min Act: -0.1700
Data Index: 5495419 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.2068. Min Act: -0.1700
Data Index: 2223768 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.2068. Min Act: -0.1700
Data Index: 6203907 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.1755. Min Act: -0.1700
Data Index: 1053941 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.1443. Min Act: -0.1700
Data Index: 2439382 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.1755. Min Act: -0.1700
Data Index: 5657790 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.1443. Min Act: -0.1700
Data Index: 6018377 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.1443. Min Act: -0.1700
Data Index: 5989670 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.1755. Min Act: -0.1700
Data Index: 6122573 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.1130. Min Act: -0.1700
Data Index: 8069432 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.0818. Min Act: -0.1700
Data Index: 7109745 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.1130. Min Act: -0.1700
Data Index: 185302 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.0818. Min Act: -0.1700
Data Index: 2699067 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.0505. Min Act: -0.1700
Data Index: 6328975 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4880. Min Range: -5.4880
Max Act: 5.0505. Min Act: -0.1700
Data Index: 6083510 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19