Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1185. Min Range: -6.1185
Max Act: 6.1185. Min Act: -0.1700
Data Index: 538629 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1185. Min Range: -6.1185
Max Act: 6.0872. Min Act: -0.1700
Data Index: 3612715 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1185. Min Range: -6.1185
Max Act: 6.1185. Min Act: -0.1700
Data Index: 3661964 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1185. Min Range: -6.1185
Max Act: 6.0560. Min Act: -0.1700
Data Index: 6709319 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.9935. Min Act: -0.1700
Data Index: 8819759 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.9622. Min Act: -0.1700
Data Index: 7618947 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.9622. Min Act: -0.1700
Data Index: 8715464 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.9310. Min Act: -0.1700
Data Index: 8819760 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.9310. Min Act: -0.1700
Data Index: 4256564 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.8997. Min Act: -0.1700
Data Index: 6660885 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.8685. Min Act: -0.1700
Data Index: 4249516 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.8997. Min Act: -0.1700
Data Index: 2391262 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.9310. Min Act: -0.1700
Data Index: 519703 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.8997. Min Act: -0.1700
Data Index: 2582635 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.8997. Min Act: -0.1700
Data Index: 2961208 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.8685. Min Act: -0.1700
Data Index: 1517262 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.8372. Min Act: -0.1700
Data Index: 8077820 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.8372. Min Act: -0.1700
Data Index: 4944526 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.8372. Min Act: -0.1700
Data Index: 7466380 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1185. Min Range: -6.1185
Max Act: 5.8685. Min Act: -0.1700
Data Index: 647578 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19