Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1025 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2120. Min Range: -7.2120
Max Act: 7.2120. Min Act: -0.1700
Data Index: 8477565 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2120. Min Range: -7.2120
Max Act: 7.0870. Min Act: -0.1700
Data Index: 7071621 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2120. Min Range: -7.2120
Max Act: 7.0870. Min Act: -0.1700
Data Index: 6815996 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2120. Min Range: -7.2120
Max Act: 7.0245. Min Act: -0.1700
Data Index: 1339891 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.9620. Min Act: -0.1700
Data Index: 8342106 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.8995. Min Act: -0.1700
Data Index: 508654 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.8995. Min Act: -0.1700
Data Index: 7679755 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.8683. Min Act: -0.1700
Data Index: 6070183 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.8058. Min Act: -0.1700
Data Index: 1946137 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.7745. Min Act: -0.1700
Data Index: 1339889 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.7745. Min Act: -0.1700
Data Index: 5661360 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.7745. Min Act: -0.1700
Data Index: 3489070 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.7433. Min Act: -0.1700
Data Index: 577162 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.7433. Min Act: -0.1700
Data Index: 2688555 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.7433. Min Act: -0.1700
Data Index: 1543142 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.6808. Min Act: -0.1700
Data Index: 1444299 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.6495. Min Act: -0.1700
Data Index: 8751962 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.6495. Min Act: -0.1700
Data Index: 3206093 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.6183. Min Act: -0.1700
Data Index: 8298815 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2120. Min Range: -7.2120
Max Act: 6.6183. Min Act: -0.1700
Data Index: 44933 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19