Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1836 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.5263. Min Act: -0.1700
Data Index: 5680072 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.4638. Min Act: -0.1700
Data Index: 1326394 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.3700. Min Act: -0.1700
Data Index: 5410348 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.3388. Min Act: -0.1700
Data Index: 8269617 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.4013. Min Act: -0.1700
Data Index: 1326390 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.4013. Min Act: -0.1700
Data Index: 4200609 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.4013. Min Act: -0.1700
Data Index: 2005601 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.3388. Min Act: -0.1700
Data Index: 7646819 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.3075. Min Act: -0.1700
Data Index: 1000239 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.3075. Min Act: -0.1700
Data Index: 1951044 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.2763. Min Act: -0.1700
Data Index: 2314114 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.2763. Min Act: -0.1700
Data Index: 278186 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.2763. Min Act: -0.1700
Data Index: 278185 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.3388. Min Act: -0.1700
Data Index: 5391548 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.2450. Min Act: -0.1700
Data Index: 3429053 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.2450. Min Act: -0.1700
Data Index: 6550535 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.2450. Min Act: -0.1700
Data Index: 1258144 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.1825. Min Act: -0.1700
Data Index: 8010159 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.2138. Min Act: -0.1700
Data Index: 4361879 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5263. Min Range: -7.5263
Max Act: 7.1513. Min Act: -0.1700
Data Index: 5780453 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19