Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2338. Min Range: -6.2338
Max Act: 6.2338. Min Act: -0.1700
Data Index: 5090818 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2338. Min Range: -6.2338
Max Act: 6.1401. Min Act: -0.1700
Data Index: 6757069 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2338. Min Range: -6.2338
Max Act: 6.1088. Min Act: -0.1700
Data Index: 7026787 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2338. Min Range: -6.2338
Max Act: 6.0463. Min Act: -0.1700
Data Index: 8488450 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2338. Min Range: -6.2338
Max Act: 6.0463. Min Act: -0.1700
Data Index: 3311904 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2338. Min Range: -6.2338
Max Act: 6.0463. Min Act: -0.1700
Data Index: 1172930 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2338. Min Range: -6.2338
Max Act: 6.0151. Min Act: -0.1700
Data Index: 6348163 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.9526. Min Act: -0.1700
Data Index: 2234313 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.9213. Min Act: -0.1700
Data Index: 2124422 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.9213. Min Act: -0.1700
Data Index: 8653595 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.8901. Min Act: -0.1700
Data Index: 7689261 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.8588. Min Act: -0.1700
Data Index: 7685697 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.8588. Min Act: -0.1700
Data Index: 6089811 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.8276. Min Act: -0.1700
Data Index: 8821511 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.8588. Min Act: -0.1700
Data Index: 3133196 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.8276. Min Act: -0.1700
Data Index: 1419459 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.7963. Min Act: -0.1700
Data Index: 1437914 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.7963. Min Act: -0.1700
Data Index: 5303790 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.7963. Min Act: -0.1700
Data Index: 784505 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2338. Min Range: -6.2338
Max Act: 5.7963. Min Act: -0.1700
Data Index: 683267 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19