Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4045 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.5839. Min Act: -0.1697
Data Index: 6252867 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.5576. Min Act: -0.1678
Data Index: 2685856 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.5138. Min Act: -0.1700
Data Index: 2503591 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4523. Min Act: -0.1699
Data Index: 173905 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4435. Min Act: -0.1679
Data Index: 37968 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4435. Min Act: -0.1653
Data Index: 5682958 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4347. Min Act: -0.1695
Data Index: 1424696 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4259. Min Act: -0.1700
Data Index: 8108511 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4171. Min Act: -0.1681
Data Index: 5477253 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4171. Min Act: -0.1693
Data Index: 7865281 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4083. Min Act: -0.1700
Data Index: 4920840 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4083. Min Act: -0.1670
Data Index: 6753375 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4083. Min Act: -0.1700
Data Index: 6606738 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.4083. Min Act: -0.1648
Data Index: 6424590 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.3995. Min Act: -0.1700
Data Index: 4558192 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.3995. Min Act: -0.1700
Data Index: 2035494 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.3995. Min Act: -0.1700
Data Index: 7067474 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.3818. Min Act: -0.1700
Data Index: 6352667 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.3995. Min Act: -0.1699
Data Index: 6859863 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5839. Min Range: -1.5839
Max Act: 1.3907. Min Act: -0.1689
Data Index: 2605356 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19