Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4847 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3322. Min Range: -4.3322
Max Act: 4.3322. Min Act: -0.1700
Data Index: 173995 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3322. Min Range: -4.3322
Max Act: 4.0821. Min Act: -0.1700
Data Index: 1347161 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3322. Min Range: -4.3322
Max Act: 4.0509. Min Act: -0.1700
Data Index: 2775601 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.9571. Min Act: -0.1700
Data Index: 3052832 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.9571. Min Act: -0.1700
Data Index: 4333551 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.9258. Min Act: -0.1700
Data Index: 713336 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.9571. Min Act: -0.1700
Data Index: 8309794 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8946. Min Act: -0.1700
Data Index: 2659180 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8946. Min Act: -0.1700
Data Index: 4578393 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8946. Min Act: -0.1700
Data Index: 3421394 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8789. Min Act: -0.1700
Data Index: 5116192 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8477. Min Act: -0.1700
Data Index: 7145657 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8320. Min Act: -0.1700
Data Index: 6881593 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8477. Min Act: -0.1700
Data Index: 6070598 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8477. Min Act: -0.1700
Data Index: 1341039 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8164. Min Act: -0.1700
Data Index: 6376362 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8164. Min Act: -0.1700
Data Index: 3370415 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8164. Min Act: -0.1700
Data Index: 5659196 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8008. Min Act: -0.1700
Data Index: 3192623 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3322. Min Range: -4.3322
Max Act: 3.8164. Min Act: -0.1700
Data Index: 2920465 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19