Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1021 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.8332. Min Act: -0.1700
Data Index: 2472228 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.8332. Min Act: -0.1700
Data Index: 8045498 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.7395. Min Act: -0.1700
Data Index: 5781843 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.6457. Min Act: -0.1700
Data Index: 2388276 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.6457. Min Act: -0.1700
Data Index: 1354037 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.5832. Min Act: -0.1700
Data Index: 1395799 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.4895. Min Act: -0.1700
Data Index: 4106285 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.4895. Min Act: -0.1700
Data Index: 3316846 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.4895. Min Act: -0.1700
Data Index: 4392303 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.4582. Min Act: -0.1700
Data Index: 6938739 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.4270. Min Act: -0.1700
Data Index: 8077766 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.4270. Min Act: -0.1700
Data Index: 3869112 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.4270. Min Act: -0.1700
Data Index: 1163954 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.3645. Min Act: -0.1700
Data Index: 4209031 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.3957. Min Act: -0.1700
Data Index: 3291479 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.3332. Min Act: -0.1700
Data Index: 6610007 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.3332. Min Act: -0.1700
Data Index: 2868867 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.3332. Min Act: -0.1700
Data Index: 8187303 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.3332. Min Act: -0.1700
Data Index: 2321492 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8332. Min Range: -6.8332
Max Act: 6.2707. Min Act: -0.1700
Data Index: 2616969 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19