Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1113 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.9114. Min Act: -0.1700
Data Index: 7545067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8943. Min Act: -0.1694
Data Index: 8831801 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8772. Min Act: -0.1670
Data Index: 5378275 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8772. Min Act: -0.1700
Data Index: 8344471 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8772. Min Act: -0.1670
Data Index: 2353115 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8772. Min Act: -0.1693
Data Index: 2353114 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8430. Min Act: -0.1700
Data Index: 929962 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8430. Min Act: -0.1700
Data Index: 6919683 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8430. Min Act: -0.1699
Data Index: 4668672 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8259. Min Act: -0.1700
Data Index: 5645223 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8259. Min Act: -0.1700
Data Index: 7750190 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8173. Min Act: -0.1698
Data Index: 972888 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8173. Min Act: -0.1700
Data Index: 6871704 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8087. Min Act: -0.1700
Data Index: 6532752 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8087. Min Act: -0.1700
Data Index: 4199431 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.8087. Min Act: -0.1699
Data Index: 929963 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.7915. Min Act: -0.1685
Data Index: 8282559 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.7915. Min Act: -0.1700
Data Index: 2334187 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.7829. Min Act: -0.1700
Data Index: 4815304 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9114. Min Range: -1.9114
Max Act: 1.7915. Min Act: -0.1699
Data Index: 3156552 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19