Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1288 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.4420. Min Act: -0.1700
Data Index: 1414958 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.3795. Min Act: -0.1700
Data Index: 4851727 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.3170. Min Act: -0.1700
Data Index: 640996 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.2857. Min Act: -0.1700
Data Index: 5150220 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.2545. Min Act: -0.1700
Data Index: 3703007 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.2545. Min Act: -0.1700
Data Index: 1417996 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.2545. Min Act: -0.1700
Data Index: 1529679 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.2545. Min Act: -0.1700
Data Index: 529525 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.2232. Min Act: -0.1700
Data Index: 4946240 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.2232. Min Act: -0.1700
Data Index: 2338616 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.1920. Min Act: -0.1700
Data Index: 7315878 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.1920. Min Act: -0.1700
Data Index: 476008 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.1920. Min Act: -0.1700
Data Index: 5814285 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.1607. Min Act: -0.1700
Data Index: 947516 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.1607. Min Act: -0.1700
Data Index: 3589741 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.1607. Min Act: -0.1700
Data Index: 1109295 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.1607. Min Act: -0.1700
Data Index: 346328 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.1295. Min Act: -0.1700
Data Index: 5073612 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.1295. Min Act: -0.1700
Data Index: 1937109 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4420. Min Range: -5.4420
Max Act: 5.1295. Min Act: -0.1700
Data Index: 2231210 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19