Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3363 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.5303. Min Act: -0.1700
Data Index: 7495562 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.5928. Min Act: -0.1700
Data Index: 4051471 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.5303. Min Act: -0.1699
Data Index: 3188128 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.4678. Min Act: -0.1700
Data Index: 256494 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.4053. Min Act: -0.1700
Data Index: 1228258 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.4053. Min Act: -0.1700
Data Index: 1697458 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.3428. Min Act: -0.1699
Data Index: 6958471 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.3428. Min Act: -0.1700
Data Index: 2112091 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.2803. Min Act: -0.1700
Data Index: 6850405 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.3428. Min Act: -0.1699
Data Index: 8435639 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.2803. Min Act: -0.1699
Data Index: 2103019 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.2178. Min Act: -0.1700
Data Index: 3570098 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.2178. Min Act: -0.1700
Data Index: 5980360 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.2178. Min Act: -0.1700
Data Index: 6976993 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.2178. Min Act: -0.1700
Data Index: 1388848 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.2178. Min Act: -0.1699
Data Index: 2026705 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.0928. Min Act: -0.1700
Data Index: 5730206 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.0928. Min Act: -0.1699
Data Index: 1535594 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.0928. Min Act: -0.1700
Data Index: 8539921 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5928. Min Range: -10.5928
Max Act: 10.1553. Min Act: -0.1698
Data Index: 8701531 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19