Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6333 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.7369. Min Act: -0.1700
Data Index: 3780134 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.7056. Min Act: -0.1700
Data Index: 8193063 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.6744. Min Act: -0.1700
Data Index: 325313 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.6431. Min Act: -0.1700
Data Index: 5937839 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.6119. Min Act: -0.1700
Data Index: 6710287 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.5806. Min Act: -0.1700
Data Index: 1202544 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.5806. Min Act: -0.1699
Data Index: 4630457 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.5494. Min Act: -0.1700
Data Index: 8748365 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.5181. Min Act: -0.1700
Data Index: 4840972 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.5181. Min Act: -0.1700
Data Index: 5519776 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.4556. Min Act: -0.1700
Data Index: 6286612 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.4556. Min Act: -0.1700
Data Index: 1155189 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.4244. Min Act: -0.1700
Data Index: 8365505 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.3931. Min Act: -0.1700
Data Index: 1265628 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.3306. Min Act: -0.1700
Data Index: 590429 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.3306. Min Act: -0.1700
Data Index: 7147467 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.2681. Min Act: -0.1700
Data Index: 8751347 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.2681. Min Act: -0.1700
Data Index: 934138 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.2681. Min Act: -0.1700
Data Index: 8543906 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7369. Min Range: -7.7369
Max Act: 7.2369. Min Act: -0.1700
Data Index: 1674756 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19