Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1316. Min Range: -8.1316
Max Act: 8.1316. Min Act: -0.1700
Data Index: 528752 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.5691. Min Act: -0.1700
Data Index: 1399981 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.3191. Min Act: -0.1700
Data Index: 7189838 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.3191. Min Act: -0.1700
Data Index: 4222160 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.2254. Min Act: -0.1700
Data Index: 4546323 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.1004. Min Act: -0.1700
Data Index: 6652581 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.1004. Min Act: -0.1700
Data Index: 2386693 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.1004. Min Act: -0.1700
Data Index: 2653477 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.1004. Min Act: -0.1700
Data Index: 1326749 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.0691. Min Act: -0.1700
Data Index: 4038061 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.0379. Min Act: -0.1700
Data Index: 1374124 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.0379. Min Act: -0.1700
Data Index: 3182000 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.0379. Min Act: -0.1700
Data Index: 3000080 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.0379. Min Act: -0.1700
Data Index: 7649329 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1316. Min Range: -8.1316
Max Act: 7.0066. Min Act: -0.1700
Data Index: 913143 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1316. Min Range: -8.1316
Max Act: 6.9754. Min Act: -0.1700
Data Index: 7158310 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1316. Min Range: -8.1316
Max Act: 6.9441. Min Act: -0.1700
Data Index: 5822407 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1316. Min Range: -8.1316
Max Act: 6.9129. Min Act: -0.1700
Data Index: 7290337 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1316. Min Range: -8.1316
Max Act: 6.9441. Min Act: -0.1700
Data Index: 5574602 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1316. Min Range: -8.1316
Max Act: 6.9441. Min Act: -0.1700
Data Index: 7565882 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19