Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1306 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.7150. Min Act: -0.1700
Data Index: 4959333 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.7462. Min Act: -0.1700
Data Index: 1970812 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.6525. Min Act: -0.1700
Data Index: 2944422 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.6525. Min Act: -0.1700
Data Index: 3937382 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.5900. Min Act: -0.1700
Data Index: 3821298 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.5900. Min Act: -0.1700
Data Index: 46415 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.5587. Min Act: -0.1700
Data Index: 7138860 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.5587. Min Act: -0.1700
Data Index: 3590012 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.5587. Min Act: -0.1700
Data Index: 2941854 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4962. Min Act: -0.1700
Data Index: 4262086 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.5275. Min Act: -0.1700
Data Index: 3679801 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4962. Min Act: -0.1700
Data Index: 6419896 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4962. Min Act: -0.1700
Data Index: 7323252 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4962. Min Act: -0.1700
Data Index: 1671720 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4650. Min Act: -0.1700
Data Index: 4634747 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4650. Min Act: -0.1700
Data Index: 4264716 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4650. Min Act: -0.1700
Data Index: 8316498 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4337. Min Act: -0.1700
Data Index: 5836973 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4337. Min Act: -0.1700
Data Index: 1748218 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4337. Min Act: -0.1700
Data Index: 6703320 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19