Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 677 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.5320. Min Act: -0.1700
Data Index: 4839341 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.2507. Min Act: -0.1700
Data Index: 1275146 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.2195. Min Act: -0.1700
Data Index: 4839339 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.2195. Min Act: -0.1700
Data Index: 179948 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.1257. Min Act: -0.1700
Data Index: 7486229 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.0632. Min Act: -0.1700
Data Index: 588911 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.0944. Min Act: -0.1700
Data Index: 7585962 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.0944. Min Act: -0.1700
Data Index: 8503006 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.0632. Min Act: -0.1700
Data Index: 2361403 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.0319. Min Act: -0.1700
Data Index: 8760745 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.0007. Min Act: -0.1700
Data Index: 2612243 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.0319. Min Act: -0.1700
Data Index: 1275132 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.0319. Min Act: -0.1700
Data Index: 7695923 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5320. Min Range: -4.5320
Max Act: 4.0007. Min Act: -0.1700
Data Index: 5492004 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5320. Min Range: -4.5320
Max Act: 3.9694. Min Act: -0.1700
Data Index: 4884089 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5320. Min Range: -4.5320
Max Act: 3.9694. Min Act: -0.1700
Data Index: 1275135 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5320. Min Range: -4.5320
Max Act: 3.9694. Min Act: -0.1700
Data Index: 8285119 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5320. Min Range: -4.5320
Max Act: 3.9694. Min Act: -0.1700
Data Index: 4235644 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5320. Min Range: -4.5320
Max Act: 3.9694. Min Act: -0.1700
Data Index: 2417947 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5320. Min Range: -4.5320
Max Act: 3.9381. Min Act: -0.1700
Data Index: 167032 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19