Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 703 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2130. Min Range: -7.2130
Max Act: 7.2130. Min Act: -0.1700
Data Index: 3635984 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2130. Min Range: -7.2130
Max Act: 7.1505. Min Act: -0.1700
Data Index: 2072474 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2130. Min Range: -7.2130
Max Act: 7.1505. Min Act: -0.1700
Data Index: 8006455 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.9630. Min Act: -0.1700
Data Index: 2152578 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.9317. Min Act: -0.1700
Data Index: 2059804 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.9317. Min Act: -0.1700
Data Index: 6176476 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.8380. Min Act: -0.1700
Data Index: 3606203 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.8380. Min Act: -0.1700
Data Index: 4897807 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.8067. Min Act: -0.1700
Data Index: 4121505 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.8067. Min Act: -0.1700
Data Index: 1044609 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.8380. Min Act: -0.1700
Data Index: 7654041 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.7755. Min Act: -0.1700
Data Index: 6229117 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.7755. Min Act: -0.1700
Data Index: 7048754 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.7755. Min Act: -0.1700
Data Index: 2263712 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.7442. Min Act: -0.1700
Data Index: 457672 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.7442. Min Act: -0.1700
Data Index: 6797443 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.7442. Min Act: -0.1700
Data Index: 4723278 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.7442. Min Act: -0.1700
Data Index: 965905 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.7442. Min Act: -0.1700
Data Index: 4562393 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2130. Min Range: -7.2130
Max Act: 6.7130. Min Act: -0.1700
Data Index: 6788889 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19