Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 87 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2206. Min Range: -6.2206
Max Act: 6.2206. Min Act: -0.1700
Data Index: 1518346 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2206. Min Range: -6.2206
Max Act: 6.2206. Min Act: -0.1700
Data Index: 8309190 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2206. Min Range: -6.2206
Max Act: 6.0644. Min Act: -0.1700
Data Index: 4586593 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.9706. Min Act: -0.1700
Data Index: 4280804 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.9081. Min Act: -0.1700
Data Index: 3820073 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.9081. Min Act: -0.1700
Data Index: 8374586 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.9394. Min Act: -0.1700
Data Index: 3017590 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.8769. Min Act: -0.1700
Data Index: 4492290 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.8769. Min Act: -0.1700
Data Index: 600676 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.9081. Min Act: -0.1700
Data Index: 1201576 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.8144. Min Act: -0.1700
Data Index: 6661810 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.8456. Min Act: -0.1700
Data Index: 3708966 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.8456. Min Act: -0.1700
Data Index: 7497986 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.8144. Min Act: -0.1700
Data Index: 5009326 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.8144. Min Act: -0.1700
Data Index: 6750870 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.8144. Min Act: -0.1700
Data Index: 2188379 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.7831. Min Act: -0.1700
Data Index: 7969137 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.7831. Min Act: -0.1700
Data Index: 7620381 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.7519. Min Act: -0.1700
Data Index: 3748930 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2206. Min Range: -6.2206
Max Act: 5.7206. Min Act: -0.1700
Data Index: 4331260 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19