Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.3002. Min Act: -0.1700
Data Index: 3535204 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.3316. Min Act: -0.1700
Data Index: 1025024 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.3159. Min Act: -0.1700
Data Index: 6083484 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.2530. Min Act: -0.1700
Data Index: 2068292 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1744. Min Act: -0.1700
Data Index: 8496748 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1587. Min Act: -0.1700
Data Index: 7965522 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1587. Min Act: -0.1700
Data Index: 2510484 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1430. Min Act: -0.1700
Data Index: 7853695 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1430. Min Act: -0.1700
Data Index: 7563334 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1272. Min Act: -0.1700
Data Index: 8388276 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1430. Min Act: -0.1700
Data Index: 8461410 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1115. Min Act: -0.1700
Data Index: 1880524 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1115. Min Act: -0.1700
Data Index: 6866970 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1115. Min Act: -0.1700
Data Index: 4274833 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1115. Min Act: -0.1700
Data Index: 4245811 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.1115. Min Act: -0.1700
Data Index: 3756430 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.0957. Min Act: -0.1700
Data Index: 8645049 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.0799. Min Act: -0.1700
Data Index: 7902977 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.0957. Min Act: -0.1700
Data Index: 738140 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3316. Min Range: -3.3316
Max Act: 3.0957. Min Act: -0.1700
Data Index: 2988944 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19