Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.8271. Min Act: -0.1700
Data Index: 4436859 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.6396. Min Act: -0.1700
Data Index: 8236491 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.4521. Min Act: -0.1700
Data Index: 2133824 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.3896. Min Act: -0.1700
Data Index: 373592 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.3896. Min Act: -0.1700
Data Index: 4773538 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.3896. Min Act: -0.1700
Data Index: 6904322 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2958. Min Act: -0.1700
Data Index: 6447207 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.3271. Min Act: -0.1700
Data Index: 4779481 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2958. Min Act: -0.1700
Data Index: 5173232 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2958. Min Act: -0.1700
Data Index: 3196803 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2958. Min Act: -0.1700
Data Index: 7295517 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2333. Min Act: -0.1700
Data Index: 393729 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2333. Min Act: -0.1700
Data Index: 4375378 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2333. Min Act: -0.1700
Data Index: 3371058 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2021. Min Act: -0.1700
Data Index: 6227020 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2021. Min Act: -0.1700
Data Index: 3064741 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2021. Min Act: -0.1700
Data Index: 6668368 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2021. Min Act: -0.1700
Data Index: 8274988 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.2021. Min Act: -0.1700
Data Index: 7097917 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8271. Min Range: -6.8271
Max Act: 6.1708. Min Act: -0.1700
Data Index: 2445453 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19