Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 695 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.3330. Min Act: -0.1700
Data Index: 6945411 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.3153. Min Act: -0.1700
Data Index: 4643414 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.3241. Min Act: -0.1700
Data Index: 7183672 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2977. Min Act: -0.1700
Data Index: 1207120 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2800. Min Act: -0.1700
Data Index: 3698443 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2977. Min Act: -0.1700
Data Index: 7168066 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2889. Min Act: -0.1699
Data Index: 2249970 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2800. Min Act: -0.1635
Data Index: 4528204 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2712. Min Act: -0.1698
Data Index: 8058772 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2712. Min Act: -0.1700
Data Index: 1313913 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2624. Min Act: -0.1700
Data Index: 4236185 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2536. Min Act: -0.1700
Data Index: 8632245 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2712. Min Act: -0.1150
Data Index: 4062190 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2624. Min Act: -0.1699
Data Index: 2275422 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2536. Min Act: -0.1700
Data Index: 4303603 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2624. Min Act: -0.1700
Data Index: 2605963 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2536. Min Act: -0.1698
Data Index: 6727513 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2448. Min Act: -0.1696
Data Index: 1347242 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2624. Min Act: -0.1700
Data Index: 7260105 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3330. Min Range: -1.3330
Max Act: 1.2448. Min Act: -0.1698
Data Index: 2763760 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19