Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 272 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1145. Min Range: -5.1145
Max Act: 5.1145. Min Act: -0.1700
Data Index: 1341376 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1145. Min Range: -5.1145
Max Act: 5.0520. Min Act: -0.1700
Data Index: 163309 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.8958. Min Act: -0.1700
Data Index: 7621804 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.8958. Min Act: -0.1700
Data Index: 3923535 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.8333. Min Act: -0.1700
Data Index: 7108994 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.8020. Min Act: -0.1700
Data Index: 3399147 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7708. Min Act: -0.1700
Data Index: 7298628 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7395. Min Act: -0.1700
Data Index: 6577061 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7395. Min Act: -0.1700
Data Index: 364586 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7708. Min Act: -0.1700
Data Index: 653361 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7395. Min Act: -0.1700
Data Index: 1874323 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7083. Min Act: -0.1700
Data Index: 7066930 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7083. Min Act: -0.1700
Data Index: 8355271 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7083. Min Act: -0.1700
Data Index: 5486301 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.6770. Min Act: -0.1700
Data Index: 4466199 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.6770. Min Act: -0.1700
Data Index: 1019928 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.6770. Min Act: -0.1700
Data Index: 2198411 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.6770. Min Act: -0.1700
Data Index: 4351606 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.6770. Min Act: -0.1700
Data Index: 3092126 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.6770. Min Act: -0.1700
Data Index: 7704828 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19