Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.3080. Min Act: -0.1700
Data Index: 2865802 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.2751. Min Act: -0.1700
Data Index: 1351542 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.2255. Min Act: -0.1699
Data Index: 4401395 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.2089. Min Act: -0.1700
Data Index: 1351540 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1923. Min Act: -0.1700
Data Index: 1890441 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1923. Min Act: -0.1700
Data Index: 1351541 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1757. Min Act: -0.1700
Data Index: 1890446 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1923. Min Act: -0.1700
Data Index: 91446 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1757. Min Act: -0.1700
Data Index: 961590 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1757. Min Act: -0.1700
Data Index: 7002974 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1591. Min Act: -0.1700
Data Index: 3496652 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1591. Min Act: -0.1700
Data Index: 2368634 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1591. Min Act: -0.1700
Data Index: 6434762 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1424. Min Act: -0.1700
Data Index: 3989064 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1424. Min Act: -0.1700
Data Index: 1890443 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1424. Min Act: -0.1700
Data Index: 5625885 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1424. Min Act: -0.1700
Data Index: 7649545 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1257. Min Act: -0.1700
Data Index: 6058020 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1424. Min Act: -0.1700
Data Index: 162673 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3080. Min Range: -2.3080
Max Act: 2.1257. Min Act: -0.1700
Data Index: 4670163 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19