Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2793 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.7401. Min Act: -0.1700
Data Index: 3896968 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.5213. Min Act: -0.1700
Data Index: 7825705 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.4276. Min Act: -0.1700
Data Index: 4480941 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.3963. Min Act: -0.1700
Data Index: 3348628 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.3651. Min Act: -0.1700
Data Index: 1151641 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.3338. Min Act: -0.1700
Data Index: 1275512 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.3338. Min Act: -0.1700
Data Index: 2687089 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.3026. Min Act: -0.1700
Data Index: 6624492 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.2401. Min Act: -0.1700
Data Index: 45832 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.2401. Min Act: -0.1700
Data Index: 7042461 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.2088. Min Act: -0.1700
Data Index: 8001404 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.2088. Min Act: -0.1700
Data Index: 853972 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.2088. Min Act: -0.1700
Data Index: 1151650 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.1776. Min Act: -0.1700
Data Index: 6154073 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.1776. Min Act: -0.1700
Data Index: 2377266 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.2088. Min Act: -0.1700
Data Index: 3280284 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.1463. Min Act: -0.1700
Data Index: 5379149 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.1463. Min Act: -0.1700
Data Index: 1094526 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.1463. Min Act: -0.1700
Data Index: 5372818 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7401. Min Range: -5.7401
Max Act: 5.1463. Min Act: -0.1700
Data Index: 3284215 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19