Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2052 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.8694. Min Act: -0.1700
Data Index: 1609467 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.6194. Min Act: -0.1700
Data Index: 3822755 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.4944. Min Act: -0.1700
Data Index: 4596032 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.4319. Min Act: -0.1700
Data Index: 5035739 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.3694. Min Act: -0.1700
Data Index: 6508442 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.2444. Min Act: -0.1700
Data Index: 8598755 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.1819. Min Act: -0.1700
Data Index: 2895698 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.1819. Min Act: -0.1700
Data Index: 767717 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.1819. Min Act: -0.1700
Data Index: 161945 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.1194. Min Act: -0.1700
Data Index: 8309655 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.1194. Min Act: -0.1700
Data Index: 6392366 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.1819. Min Act: -0.1700
Data Index: 5335002 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.1194. Min Act: -0.1700
Data Index: 119195 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8694. Min Range: -9.8694
Max Act: 8.9944. Min Act: -0.1700
Data Index: 6466609 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8694. Min Range: -9.8694
Max Act: 8.9944. Min Act: -0.1700
Data Index: 1438485 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.0569. Min Act: -0.1700
Data Index: 287682 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.0569. Min Act: -0.1700
Data Index: 2607332 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8694. Min Range: -9.8694
Max Act: 9.0569. Min Act: -0.1700
Data Index: 8085599 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8694. Min Range: -9.8694
Max Act: 8.9944. Min Act: -0.1700
Data Index: 5786047 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8694. Min Range: -9.8694
Max Act: 8.9944. Min Act: -0.1700
Data Index: 6243295 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19