Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.5040. Min Act: -0.1700
Data Index: 8506196 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.5040. Min Act: -0.1700
Data Index: 498254 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.5040. Min Act: -0.1700
Data Index: 2524319 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.3477. Min Act: -0.1700
Data Index: 5817494 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.3477. Min Act: -0.1700
Data Index: 4308282 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.2852. Min Act: -0.1700
Data Index: 3412002 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.2540. Min Act: -0.1700
Data Index: 3616838 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.2227. Min Act: -0.1700
Data Index: 4202487 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.2227. Min Act: -0.1700
Data Index: 8002697 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1602. Min Act: -0.1700
Data Index: 4518755 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1914. Min Act: -0.1700
Data Index: 2878116 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1602. Min Act: -0.1700
Data Index: 5915919 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1602. Min Act: -0.1700
Data Index: 6828954 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1289. Min Act: -0.1700
Data Index: 5009315 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1602. Min Act: -0.1700
Data Index: 3502173 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1289. Min Act: -0.1700
Data Index: 8257564 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1289. Min Act: -0.1700
Data Index: 2627564 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1289. Min Act: -0.1700
Data Index: 3361280 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1289. Min Act: -0.1700
Data Index: 7226175 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5040. Min Range: -4.5040
Max Act: 4.1602. Min Act: -0.1700
Data Index: 5451052 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19