Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.5091. Min Act: -0.1700
Data Index: 2592645 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.4154. Min Act: -0.1700
Data Index: 2095132 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.2591. Min Act: -0.1700
Data Index: 6720159 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.2591. Min Act: -0.1700
Data Index: 6591366 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.2591. Min Act: -0.1700
Data Index: 1351607 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.2904. Min Act: -0.1700
Data Index: 4917679 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.2279. Min Act: -0.1700
Data Index: 7585126 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.2279. Min Act: -0.1700
Data Index: 8510770 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.1966. Min Act: -0.1700
Data Index: 8339842 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.1654. Min Act: -0.1700
Data Index: 8434798 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.1654. Min Act: -0.1700
Data Index: 2196180 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.1341. Min Act: -0.1700
Data Index: 8322334 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.1654. Min Act: -0.1700
Data Index: 4324871 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.1341. Min Act: -0.1700
Data Index: 7243324 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.1341. Min Act: -0.1700
Data Index: 3866591 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.1341. Min Act: -0.1700
Data Index: 5035218 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.0716. Min Act: -0.1700
Data Index: 3002945 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.0404. Min Act: -0.1700
Data Index: 3361711 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.1029. Min Act: -0.1700
Data Index: 3630133 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5091. Min Range: -7.5091
Max Act: 7.0404. Min Act: -0.1700
Data Index: 4711204 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19