Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1305 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.4360. Min Act: -0.1700
Data Index: 401572 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.3110. Min Act: -0.1700
Data Index: 1627758 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.3110. Min Act: -0.1700
Data Index: 1160177 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.3110. Min Act: -0.1700
Data Index: 8072876 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.3110. Min Act: -0.1700
Data Index: 6572150 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.3110. Min Act: -0.1700
Data Index: 5273380 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.3110. Min Act: -0.1700
Data Index: 60084 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.1860. Min Act: -0.1700
Data Index: 813455 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.2485. Min Act: -0.1700
Data Index: 3762795 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.1860. Min Act: -0.1700
Data Index: 4243228 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.1860. Min Act: -0.1700
Data Index: 1646623 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.1860. Min Act: -0.1700
Data Index: 2690700 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.1860. Min Act: -0.1700
Data Index: 5783839 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.0610. Min Act: -0.1700
Data Index: 3633419 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.1235. Min Act: -0.1700
Data Index: 8562326 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.0610. Min Act: -0.1700
Data Index: 1799128 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.0610. Min Act: -0.1700
Data Index: 5958377 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.0610. Min Act: -0.1700
Data Index: 6192442 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4360. Min Range: -9.4360
Max Act: 9.0610. Min Act: -0.1700
Data Index: 4059492 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4360. Min Range: -9.4360
Max Act: 8.9985. Min Act: -0.1700
Data Index: 828075 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19